100% found this document useful (2 votes)

297 views49 pages

Download ebooks file Deep Learning with R 1st Edition François Chollet all chapters

Chollet

Uploaded by

bleemjirikcr

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

100% found this document useful (2 votes)

297 views49 pages

Download ebooks file Deep Learning with R 1st Edition François Chollet all chapters

Chollet

Uploaded by

bleemjirikcr

We take content rights seriously. If you suspect this is your content, claim it here.

Available Formats

Download as PDF, TXT or read online on Scribd

You are on page 1/ 49

Download the Full Version of textbook for Fast Typing at textbookfull.

com

Deep Learning with R 1st Edition François Chollet

https://textbookfull.com/product/deep-learning-with-r-1st-
edition-francois-chollet/

OR CLICK BUTTON

DOWNLOAD NOW

Download More textbook Instantly Today - Get Yours Now at textbookfull.com

Recommended digital products (PDF, EPUB, MOBI) that
you can download immediately if you are interested.

Deep Learning with Python 1st Edition François Chollet

https://textbookfull.com/product/deep-learning-with-python-1st-
edition-francois-chollet/

textboxfull.com

Deep Learning with Python MEAP 2nd Edition Francois

Chollet

https://textbookfull.com/product/deep-learning-with-python-meap-2nd-
edition-francois-chollet/

textboxfull.com

R Deep Learning Essentials 1st Edition Wiley

https://textbookfull.com/product/r-deep-learning-essentials-1st-
edition-wiley/

textboxfull.com

Deep Learning Pipeline: Building a Deep Learning Model

with TensorFlow 1st Edition Hisham El-Amir

https://textbookfull.com/product/deep-learning-pipeline-building-a-
deep-learning-model-with-tensorflow-1st-edition-hisham-el-amir/

textboxfull.com
Deep Learning With Pytorch 1st Edition Eli Stevens

https://textbookfull.com/product/deep-learning-with-pytorch-1st-
edition-eli-stevens/

textboxfull.com

Introduction to Deep Learning Using R: A Step-by-Step

Guide to Learning and Implementing Deep Learning Models
Using R Taweh Beysolow Ii
https://textbookfull.com/product/introduction-to-deep-learning-using-
r-a-step-by-step-guide-to-learning-and-implementing-deep-learning-
models-using-r-taweh-beysolow-ii/
textboxfull.com

Probabilistic Deep Learning with Python 1st Edition Oliver

Duerr

https://textbookfull.com/product/probabilistic-deep-learning-with-
python-1st-edition-oliver-duerr/

textboxfull.com

Deep Learning with Structured Data 1st Edition Mark Ryan

https://textbookfull.com/product/deep-learning-with-structured-
data-1st-edition-mark-ryan/

textboxfull.com

Deep Learning with Structured Data 1st Edition Mark Ryan

https://textbookfull.com/product/deep-learning-with-structured-
data-1st-edition-mark-ryan-2/

textboxfull.com
MEAP Edition
Manning Early Access Program
Deep Learning with R
Version 1

Copyright 2017 Manning Publications

For more information on this and other Manning titles go to

www.manning.com

©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
welcome
Thank you for purchasing the MEAP for Deep Learning with R. If you are looking for a
resource to learn about deep learning from scratch and to quickly become able to use this
knowledge to solve real-world problems, you have found the right book. Deep Learning
with R is meant for statisticians, analysts, engineers and students with a reasonable amount
of R experience, but no significant knowledge of machine learning and deep learning. This
book is an adaptation of my previously published Deep Learning with Python, with all of
the code examples using the R interface to Keras. The goal of the book is to provide a
learning resource for the R community that goes all the way from basic theory to advanced
practical applications.
Deep learning is an immensely rich subfield of machine learning, with powerful
applications ranging from machine perception to natural language processing, all the way up
to creative AI. Yet, its core concepts are in fact very simple. Deep learning is often
presented as shrouded in a certain mystique, with references to algorithms that “work like
the brain”, that “think” or “understand”. Reality is however quite far from this science-
fiction dream, and I will do my best in these pages to dispel these illusions. I believe that
there are no difficult ideas in deep learning, and that’s why I started this book, based on
premise that all of the important concepts and applications in this field could be taught to
anyone, with very few prerequisites.
This book is structured around a series of practical code examples, demonstrating on real-
world problems every the notions that gets introduced. I strongly believe in the value of
teaching using concrete examples, anchoring theoretical ideas into actual results and
tangible code patterns. These examples all rely on Keras, the deep learning library. When I
released the initial version of Keras almost two years ago, little did I know that it would
quickly skyrocket to become one of the most widely used deep learning frameworks. A big
part of that success is that Keras has always put ease of use and accessibility front and
center. This same reason is what makes Keras a great library to get started with deep
learning, and thus a great fit for this book. By the time you reach the end of this book, you
will have become a Keras expert.
I hope that you will this book valuable —deep learning will definitely open up new
intellectual perspectives for you, and in fact it even has the potential to transform your
career, being the most in-demand scientific specialization these days. I am looking forward
to your reviews and comments. Your feedback is essential in order to write the best possible
book, that will benefit the greatest number of people.

— François Chollet

This chapter covers

What is deep learning?

High-level definitions of fundamental concepts

1
Timeline of the development of machine learning
Key factors behind deep learning’s rising popularity and future
potential

In the past few years, artificial intelligence (AI) has been a subject of intense media hype.
Machine learning, deep learning, and AI come up in countless articles, often outside of
technology-minded publications. We’re being promised a future of intelligent chatbots,
self-driving cars, and virtual assistants—a future sometimes painted in a grim light and
other times as an utopia, where human jobs would be scarce and most economic activity
would be handled by robots or AI agents. This chapter provides essential context around
artificial intelligence, machine learning, and deep learning.

1.1 Artificial intelligence, machine learning, and deep learning

As a future or current practitioner of machine learning, it’s important to be able to
recognize the signal in the noise so that you can tell world-changing developments from
mere overhyped press releases. Our future is at stake, and it’s a future in which you have
an active role to play: after reading this book, you’ll be one of those who develop the
AIs. So let’s tackle these questions: What has deep learning achieved so far? How
significant is it? Where are we headed next? Should you believe the hype?
First, we need to define clearly what we’re talking about when we mention AI. What
are artificial intelligence, machine learning, and deep learning (see figure 1.1)? How do
they relate to each other?

Figure 1.1 Artificial intelligence, machine learning, and deep learning

1.1.1 Artificial intelligence

Artificial intelligence was born in the 1950s, when a handful of pioneers from the nascent
field of computer science started asking whether computers could be made to "think"—a
question whose ramifications we’re still exploring today. A concise definition of the field
would be as follows: the effort to automate intellectual tasks normally performed by
humans. As such, AI is a general field that encompasses machine learning and deep
learning, but that also includes many more approaches that don’t involve any learning.
Early chess programs, for instance, only involved hard-coded rules crafted by
programmers, and didn’t qualify as machine learning. For a fairly long time, many
experts believed that human-level artificial intelligence could be achieved by having
programmers handcraft a sufficiently large set of explicit rules for manipulating
knowledge. This approach is known as symbolic AI, and it was the dominant paradigm in
AI from the 1950s to the late 1980s. It reached its peak popularity during the expert
systems boom of the 1980s.
Although symbolic AI proved suitable to solve well-defined, logical problems, such
as playing chess, it turned out to be intractable to figure out explicit rules for solving
more complex, fuzzy problems, such as image classification, speech recognition, and
language translation. A new approach arose to take symbolic AI’s place: machine
learning.

1.1.2 Machine Learning

In Victorian England, Lady Ada Lovelace was a friend and collaborator of Charles
Babbage, the inventor of the Analytical Engine: the first known general-purpose,
mechanical computer. Although visionary and far ahead of its time, the Analytical
Engine wasn’t meant as a general-purpose computer when it was designed in the 1830s
and 1840s, because the concept of general-purpose computation was yet to be invented. It
was merely meant as a way to use mechanical operations to automate certain
computations from the field of mathematical analysis—hence the name Analytical
Engine. In 1843, Ada Lovelace remarked on the invention, "The Analytical Engine has
no pretensions whatever to originate anything. It can do whatever we know how to order
it to perform.… Its province is to assist us in making available what we’re already
acquainted with."
This remark was later quoted by AI pioneer Alan Turing as "Lady Lovelace’s
objection" in his landmark 1950 paper "Computing Machinery and Intelligence,"1 which
introduced the Turing test as well as key concepts that would come to shape AI. Turing
was quoting Ada Lovelace while pondering whether general-purpose computers could be
capable of learning and originality, and he came to the conclusion that they could.
Footnote 1mA. M. Turing, "Computing Machinery and Intelligence," Mind 59, no. 236 (1950): 433-460.

Machine learning arises from this question: could a computer go beyond "what we
know how to order it to perform" and learn on its own how to perform a specified task?
Could a computer surprise us? Rather than programmers crafting data-processing rules
by hand, could a computer automatically learn these rules by looking at data?
This question opens the door to a new programming paradigm. In classical
programming, the paradigm of symbolic AI, humans input rules (a program) and data to
be processed according to these rules, and out come answers (see figure 1.2). With
machine learning, humans input data as well as the answers expected from the data, and
out come the rules. These rules can then be applied to new data to produce original
answers.

Figure 1.2 Machine learning: a new programming paradigm

A machine-learning system is trained rather than explicitly programmed. It’s

presented with many examples relevant to a task, and it finds statistical structure in these
examples that eventually allows the system to come up with rules for automating the
task. For instance, if you wished to automate the task of tagging your vacation pictures,

you could present a machine-learning system with many examples of pictures already
tagged by humans, and the system would learn statistical rules for associating specific
pictures to specific tags.
Although machine learning only started to flourish in the 1990s, it has quickly
become the most popular and most successful subfield of AI, a trend driven by the
availability of faster hardware and larger datasets. Machine learning is tightly related to
mathematical statistics, but it differs from statistics in several important ways. Unlike
statistics, machine learning tends to deal with large, complex datasets (such as a dataset
of millions of images, each consisting of tens of thousands of pixels) for which classical
statistical analysis such as Bayesian analysis would be impractical. As a result, machine
learning, and especially deep learning, exhibits comparatively little mathematical
theory—maybe too little—and is engineering oriented. It’s a hands-on discipline in
which ideas are proven empirically much more often than theoretically.

1.1.3 Learning representations from data

To define deep learning and understand the difference between deep learning and other
machine-learning approaches, first we need some idea of what machine-learning
algorithms do. We just stated that machine learning discovers rules to execute a
data-processing task, given examples of what’s expected. So, to do machine learning, we
need three things:

Input data points—For instance, if the task is speech recognition, these data points could
be sound files of people speaking. If the task is image tagging, they could be picture files.
Examples of the expected output—In a speech-recognition task, these could be
human-generated transcripts of sound files. In an image task, expected outputs could tags
such as "dog", "cat", and so on.
A way to measure whether the algorithm is doing a good job—This is necessary in order
to determine the distance between the algorithm’s current output and its expected output.
The measurement is used as a feedback signal to adjust the way the algorithm works.
This adjustment step is what we call learning.

A machine-learning model transforms its input data into meaningful output, a process
that is "learned" from exposure to known examples of inputs and outputs. Therefore, the
central problem in machine learning and deep learning is to meaningfully transform data:
in other words, to learn useful representations of the input data at hand—representations
that get us closer to the expected output. Before we go any further: what’s a
representation? At its core, it’s a different way to look at data—to represent or encode
data. For instance, a color image can be encoded in the RGB format (red-green-blue) or
in the HSV format (hue-saturation-value): these are two different representations of the
same data. Some tasks that may be difficult with one representation can become easy
with another. For example, the task "select all red pixels in the image" is simpler in the
RBG format, whereas "make the image less saturated" is simpler in the HSV format.
Machine-learning models are all about finding appropriate representations for their input
data—transformations of the data that make it more amenable to the task at hand, such as
a classification task.
©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
5

Let’s make this concrete. Consider an x axis, a y axis, and some points represented by
their coordinates in the (x, y) system, as shown in figure 1.3.

Figure 1.3 Some sample data

As you can see, we have a few white points and a few black points. Let’s say we want
to develop an algorithm that can take the coordinates (x, y) of a point and output whether
that point is likely to be black or to be white. In this case,

The inputs are the coordinates of our points.

The expected outputs are the colors of our points.
A way to measure whether our algorithm is doing a good job could be, for instance, the
percentage of points that are being correctly classified.

What we need here is a new representation of our data that cleanly separates the white
points from the black points. One transformation we could use, among many other
possibilities, would be a coordinate change, illustrated in figure 1.4.

Figure 1.4 Coordinate change

In this new coordinate system, the coordinates of our points can be said to be a new
representation of our data. And it’s a good one! With this representation, the black/white
classification problem can be expressed as a simple rule: black points are such that x 0 or
"white points are such that x < 0". This new representation basically solves the
classification problem.
In this case, we defined the coordinate change by hand. But if instead we tried
systematically searching for different possible coordinate changes, and used as feedback
©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
6

the percentage of points being correctly classified, then we would be doing machine
learning. Learning, in the context of machine learning, describes an automatic search
process for better representations.
All machine-learning algorithms consist of automatically finding such
transformations that turn data into more useful representations for a given task. These
operations can be coordinate changes, as you just saw, or linear projections (which may
destroy information), translations, nonlinear operations (such as select all points such that
x 0), and so on. Machine-learning algorithms aren’t usually creative in finding these
transformations; they’re merely searching through a predefined set of operations, called a
hypothesis space.
So that’s what machine learning is, technically: searching for useful representations
of some input data, within a predefined space of possibilities, using guidance from some
feedback signal. This simple idea allows for solving a remarkably broad range of
intellectual tasks, from speech recognition to autonomous car driving.
Now that you understand what we mean by learning, let’s take a look at what makes
deep learning special.

1.1.4 The "deep" in deep learning

Deep learning is a specific subfield of machine learning: a new take on learning
representations from data that puts an emphasis on learning successive layers of
increasingly meaningful representations. The deep in deep learning isn’t a reference to
any kind of deeper understanding achieved by the approach; rather, it stands for this idea
of successive layers of representations. How many layers contribute to a model of the
data is called the depth of the model. Other appropriate names for the field could have
been layered representations learning and hierarchical representations learning. Modern
deep learning often involves tens or even hundreds of successive layers of
representation—and they’re all learned automatically from exposure to training data.
Meanwhile, other approaches to machine learning tend to focus on learning only one or
two layers of representation of the data; hence they’re sometimes called shallow learning
.
In deep learning, these layered representations are (almost always) learned via models
called neural networks, structured in literal layers stacked one after the other. The term
neural network is a reference to neurobiology, but although some of the central concepts
in deep learning were developed in part by drawing inspiration from our understanding of
the brain, deep learning models are not models of the brain. There’s no evidence that the
brain implements anything like the learning mechanisms used in modern deep-learning
models. You may come across pop-science articles proclaiming that deep learning works
like the brain or was modeled after the brain, but that isn’t the case. It would be
confusing and counterproductive for newcomers to the field to think of deep learning as
being in any way related to the neurobiology; you don’t need that shroud of "just like our

minds" mystique and mystery, and you may as well forget anything you may have read
about hypothetical links between deep learning and biology. For our purposes, deep
learning is a mathematical framework for learning representations from data.
What do the representations learned by a deep-learning algorithm look like? Let’s
examine how a network several layers deep (see figure 1.5) transforms an image of a
digit in order to recognize what digit it is.

Figure 1.5 A deep neural network for digit classification

As you can see in figure 1.6, the network transforms the digit image into
representations that are increasingly different from the original image and increasingly
informative about the final result. You can think of a deep network as a multistage
information-distillation operation, where information goes through successive filters and
comes out increasingly purified (that is, useful with regard to some task).

Figure 1.6 Deep representations learned by a digit-classification model

So that’s what deep learning is, technically: a multistage way to learn data
©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
8

representations. It’s a simple idea—but, as it turns out, very simple mechanisms,

sufficiently scaled, can end up looking like magic.

1.1.5 Understanding how deep learning works, in three figures

At this point, you know that machine learning is about mapping inputs (such as images)
to targets (such as the label "cat"), which is done by observing many examples of input
and targets. You also know that deep neural networks do this input-to-target mapping via
a deep sequence of simple data transformations (layers) and that these data
transformations are learned by exposure to examples. Now let’s look at how this learning
happens, concretely.
The specification of what a layer does to its input data is stored in the layer’s weights,
which in essence are a bunch of numbers. In technical terms, we’d say that the
transformation implemented by a layer is parametrized by its weights (see figure 1.7).
(Weights are also sometimes called the parameters of a layer.) In this context, learning
means finding a set of values for the weights of all layers in a network, such that the
network will correctly map example inputs to their associated targets. But here’s the
thing: a deep neural network can contain tens of millions of parameters. Finding the
correct value for all of them may seem like a daunting task, especially given that
modifying the value of one parameter will affect the behavior of all others!

Figure 1.7 A neural network is parametrized by its weights.

To control something, first you need to be able to observe it. To control the output of
a neural network, you need to be able to measure how far this output is from what you
expected. This is the job of the loss function of the network, also called the objective
function. The loss function takes the predictions of the network and the true target (what
you wanted the network to output) and computes a distance score, capturing how well the
network has done on this specific example (see figure 1.8).

Figure 1.8 A loss function measures the quality of the network’s output.

The fundamental trick in deep learning is to use this score as a feedback signal to
adjust the value of the weights a little, in a direction that will lower the loss score for the
current example (see figure 1.9). This adjustment is the job of the optimizer, which
implements what’s called the backpropagation algorithm: the central algorithm in deep
learning. The next chapter will explain in more detail how backpropagation works.

Figure 1.9 The loss score is used as a feedback signal to adjust the weights.

Initially, the weights of the network are assigned random values, so the network
merely implements a series of random transformations. Naturally, its output is far from
what it should ideally be, and the loss score is accordingly very high. But with every
example the network processes, the weights are adjusted a little in the correct direction,
and the loss score decreases. This is the training loop, which, repeated a sufficient
number of times (typically tens of iterations over thousands of examples), yields weight
values that minimize the loss function. A network with a minimal loss is one for which
the outputs are as close as they can be to the targets: a trained network. Once again, a
simple mechanism that, once scaled, ends up looking like magic.

1.1.6 What deep learning has achieved so far

Although deep learning is a fairly old subfield of machine learning, it only rose to
prominence in the early 2010s. In the few years since, it has achieved nothing short of a
revolution in the field, with remarkable results on perceptual problems such as seeing and
hearing—problems involving skills that seem natural and intuitive to humans but have
long been elusive for machines.
In particular, deep learning has achieved the following breakthroughs, all in
historically difficult areas of machine learning:

Near-human-level image classification

Near-human-level speech recognition
Near-human-level handwriting transcription
Improved machine translation
Improved text-to-speech conversion
Digital assistants such as Google Now and Amazon Alexa
Near-human-level autonomous driving
Improved ad targeting, as used by Google, Baidu, and Bing
Improved search results on the Web
Ability to answer natural-language questions
Superhuman Go playing

We’re still exploring the full extent of what deep learning can do. We’ve started
applying it to a wide variety of problems outside of machine perception and
natural-language understanding, such as formal reasoning. If successful, this may herald
an age where deep learning assists humans in doing science, developing software, and
more.

1.1.7 Don’t believe the short-term hype

Although deep learning has led to remarkable achievements in recent years, expectations
for what the field will be able to achieve in the next decade tend to run much higher than
what will turn out to be possible. Although some world-changing applications like
autonomous cars are already within reach, many more are likely to remain elusive for a
long time, such as believable dialogue systems, human-level machine translation across
arbitrary languages, and human-level natural-language understanding. In particular, talk
of human-level general intelligence shouldn’t be taken too seriously. The risk with high
expectations for the short term is that, as technology fails to deliver, research investment
will dry up, slowing progress for a long time.
This has happened before. Twice in the past, AI went through a cycle of intense
optimism followed by disappointment and skepticism, with a dearth of funding as a
result. It started with symbolic AI in the 1960s. In those early days, projections about AI
were flying high. One of the best-known pioneers and proponents of the symbolic AI
approach was Marvin Minsky, who claimed in 1967, "Within a generation … the
problem of creating 'artificial intelligence' will substantially be solved." Three years later,
in 1970, he made a more precisely quantified prediction: "In from three to eight years we
©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
11

will have a machine with the general intelligence of an average human being." In 2016,
such an achievement still appears to be far in the future—so far that we have no way to
predict how long it will take—but in the 1960s and early 1970s, several experts believed
it to be right around the corner (as do many people today). A few years later, as these
high expectations failed to materialize, researchers and government funds turned away
from the field, marking the start of the first AI winter (a reference to a nuclear winter,
because this was shortly after the height of the Cold War).
It wouldn’t be the last one. In the 1980s, a new take on symbolic AI, expert systems,
started gathering steam among large companies. A few initial success stories triggered a
wave of investment, with corporations around the world starting their own in-house AI
departments to develop expert systems. Around 1985, companies were spending over $1
billion each year on the technology; but by the early 1990s, these systems had proven
expensive to maintain, difficult to scale, and limited in scope, and interest died down.
Thus began the second AI winter.
We may be currently witnessing the third cycle of AI hype and disappointment—and
we’re still in the phase of intense optimism. It’s best to moderate our expectations for the
short term and make sure people less familiar with the technical side of the field have a
clear idea of what deep learning can and can’t deliver.

1.1.8 The promise of AI

Although we may have unrealistic short-term expectations for AI, the long-term picture
is looking bright. We’re only just getting started in applying deep learning to many
important problems for which it could prove transformative, from medical diagnoses to
digital assistants. AI research has been moving forward amazingly quickly in the past
five years, in large part due to a level of funding never seen before in the short history of
AI, but so far relatively little of this progress has made its way into the products and
processes that form our world. Most of the research findings of deep learning aren’t yet
applied, or at least not applied to the full range of problems they can solve across all
industries. Your doctor doesn’t yet use AI, and neither does your accountant. You
probably don’t use AI technologies in your day-to-day life. Of course, you can ask your
smartphone simple questions and get reasonable answers, you can get fairly useful
product recommendations on Amazon.com, and you can search for "birthday" on Google
Photos and instantly find those pictures of your daughter’s birthday party from last
month. That’s a far cry from where such technologies used to stand. But such tools are
still only accessory to our daily lives. AI has yet to transition to being central to the way
we work, think, and live.
Right now, it may seem hard to believe that AI could have a large impact on our
world, because it isn’t yet widely deployed—much as, back in 1995, it would have been
difficult to believe in the future impact of the internet. Back then, most people didn’t see
how the internet was relevant to them and how it was going to change their lives. The
same is true for deep learning and AI today. But make no mistake: AI is coming. In a
not-so-distant future, AI will be your assistant, even your friend; it will answer your
©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
12

questions, help educate your kids, and watch over your health. It will deliver your
groceries to your door and drive you from point A to point B. It will be your interface to
an increasingly complex and increasingly information-intensive world. And, even more
important, AI will help humanity as a whole move forward, by assisting human scientists
in new breakthrough discoveries across all scientific fields, from genomics to
mathematics.
On the way, we may face a few setbacks and maybe a new AI winter—in much the
same way the internet industry was overhyped in 1998–1999 and suffered from a crash
that dried up investment throughout the early 2000s. But we’ll get there eventually. AI
will end up being applied to nearly every process that makes up our society and our daily
lives, much like the internet today.
Don’t believe the short-term hype, but do believe in the long-term vision. It may take
a while for AI to be deployed to its true potential—a potential the full extent of which no
one has yet dared to dream—but AI is coming, and it will transform our world in a
fantastic way.

1.2 Before deep learning: a brief history of machine learning

Deep learning has reached a level of public attention and industry investment never seen
before in the history of AI, but it isn’t the first successful form of machine learning. It’s
safe to say that most of the machine-learning algorithms used in the industry today aren’t
deep-learning algorithms. Deep learning isn’t always the right tool for the
job—sometimes there isn’t enough data for deep learning to be applicable, and
sometimes the problem is better solved by a different algorithm. If deep learning is your
first contact with machine learning, then you may find yourself in a situation where all
you have is the deep-learning hammer, and every machine-learning problem starts to
look like a nail. The only way not to fall into this trap is to be familiar with other
approaches and practice them when appropriate.
A detailed discussion of classical machine-learning approaches is outside of the scope
of this book, but we’ll briefly go over them and describe the historical context in which
they were developed. This will allow us to place deep learning in the broader context of
machine learning and better understand where deep learning comes from and why it
matters.

1.2.1 Probabilistic modeling

Probabilistic modeling is the application of the principles of statistics to data analysis. It
was one of the earliest forms of machine learning, and it’s still widely used to this day.
One of the best-known algorithms in this category is the Naive Bayes algorithm.
Naive Bayes is a type of machine-learning classifier based on applying the Bayes
theorem while assuming that the features in the input data are all independent (a strong,
or "naive" assumption, which is where the name comes from). This form of data analysis
predates computers and was applied by hand decades before its first computer

implementation (most likely dating back to the 1950s). The Bayes theorem and the
foundations of statistics date back to the 18th century, and these are all you need to start
using Naive Bayes classifiers.
A closely related model is the logistic regression (logreg for short), which is
sometimes considered to be the "hello world" of modern machine learning. Don’t be
misled by its name—logreg is a classification algorithm rather than a regression
algorithm. Much like Naive Bayes, logreg predates computing by a long time, yet it’s
still useful to this day, thanks to its simple and versatile nature. It’s often the first thing a
data scientist will try on a dataset to get a feel for the classification task at hand.

1.2.2 Early neural networks

Early iterations of neural networks have been completely supplanted by the modern
variants covered in these pages, but it’s helpful to be aware of how deep learning
originated. Although the core ideas of neural networks were investigated in toy forms as
early as the 1950s, the approach took decades to get started. For a long time, the missing
piece was an efficient way to train large neural networks. This changed in the mid 1980s,
when multiple people independently rediscovered the backpropagation algorithm—a
way to train chains of parametric operations using gradient-descent optimization (later in
the book, we’ll precisely define these concepts)--and started applying it to neural
networks.
The first successful practical application of neural nets came in 1989 from Bell Labs,
when Yann LeCun combined the earlier ideas of convolutional neural networks and
backpropagation, and applied them to the problem of classifying handwritten digits. The
resulting network, dubbed LeNet, was used by the United States Postal Service in the
1990s to automate the reading of ZIP codes on mail envelopes.

1.2.3 Kernel methods

As neural networks started to gain some respect among researchers in the 1990s, thanks
to this first success, a new approach to machine learning rose to fame and quickly sent
neural nets back to oblivion: kernel methods. Kernel methods are a group of classification
algorithms, the best known of which is the support vector machine (SVM). The modern
formulation of an SVM was developed by Vladimir Vapnik and Corinna Cortes in the
early 1990s at Bell Labs and published in 1995,2 although an older linear formulation
was published by Vapnik and Chervonenkis as early as 1963.3
Footnote 2mVladimir Vapnik and Corinna Cortes, "Support-Vector Networks," Machine Learning 20, no.
3 (1995): 273–297.

Footnote 3mVladimir Vapnik and Alexey Chervonenkis, "A Note on One Class of Perceptrons,"
Automation and Remote Control 25 (1964).

SVMs aim at solving classification problems by finding good decision boundaries

(see figure 1.10) between two sets of points belonging to two different categories. A

decision boundary can be thought of as a line or surface separating your training data into
two spaces corresponding to two categories. To classify new data points, you just need to
check which side of the decision boundary they fall on.

Figure 1.10 A decision boundary

SVMs proceed to find these boundaries in two steps:

1. The data is mapped to a new high-dimensional representation where the decision

boundary can be expressed as a hyperplane (if the data was two-dimensional, as in figure
1.10, a hyperplane would be a straight line).
2. A good decision boundary (a separation hyperplane) is computed by trying to maximize
the distance between the hyperplane and the closest data points from each class, a step
called maximizing the margin. This allows the boundary to generalize well to new
samples outside of the training dataset.

The technique of mapping data to a high-dimensional representation where a

classification problem becomes simpler may look good on paper, but in practice it’s often
computationally intractable. That’s where the kernel trick comes in (the key idea that
kernel methods are named after). Here’s the gist of it: to find good decision hyperplanes
in the new representation space, you don’t have to explicitly compute the coordinates of
your points in the new space; you just need to compute the distance between pairs of
points in that space, which can be done efficiently using a kernel function. A kernel
function is a computationally tractable operation that maps any two points in your initial
space to the distance between these points in your target representation space, completely
bypassing the explicit computation of the new representation. Kernel functions are
typically crafted by hand rather than learned from data—in the case of an SVM, only the
separation hyperplane is learned.
At the time they were developed, SVMs exhibited state-of-the-art performance on
simple classification problems and were one of the few machine-learning methods
backed by extensive theory and amenable to serious mathematical analysis, making them
well understood and easily interpretable. Because of these useful properties, SVMs
became extremely popular in the field for a long time.
But SVMs proved hard to scale to large datasets and didn’t provide good results for
©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
15

perceptual problems such as image classification. Because an SVM is a shallow method,

applying an SVM to perceptual problems requires first extracting useful representations
manually (a step called feature engineering), which is difficult and brittle.

1.2.4 Decision trees, random forests, and gradient boosting machines

Decision trees are flowchart-like structures that let you classify input data points or
predict output values given inputs (see figure 1.11). They’re easy to visualize and
interpret. Decisions trees learned from data began to receive significant research interest
in the 2000s, and by 2010 they were often preferred to kernel methods.

Figure 1.11 A decision tree: the parameters that are learned are the questions about the
data. A question could be, for instance, "Is coefficient 2 in the data higher than 3.5?"

In particular, the Random Forest algorithm introduced a robust, practical take on

decision-tree learning that involves building a large number of specialized decision trees
and then ensembling their outputs. Random forests are applicable to a wide range of
problems—you could say that they’re almost always the second-best algorithm for any
shallow machine-learning task. When the popular machine-learning competition website
Kaggle (kaggle.com) got started in 2010, random forests quickly became a favorite on
the platform—until 2014, when gradient boosting machines took over. A gradient
boosting machine, much like a random forest, is a machine-learning technique based on
ensembling weak prediction models, generally decision trees. It uses gradient boosting, a
way to improve any machine-learning model by iteratively training new models that
specialize in addressing the weak points of the previous models. Applied to decision
trees, the use of the gradient boosting technique results in models that strictly outperform
random forests most of the time, while having similar properties. It may be one of the
best, if not the best, algorithm for dealing with nonperceptual data today. Alongside deep
learning, it’s one of the most commonly used techniques in Kaggle competitions.

1.2.5 Back to neural networks

Around 2010, although neural networks were almost completely shunned by the
scientific community at large, a number of people still working on neural networks
started to make important breakthroughs: the groups of Geoffrey Hinton at the University
of Toronto, Yoshua Bengio at the University of Montreal, Yann LeCun at New York
University, and IDSIA in Switzerland.
In 2011, Dan Ciresan from IDSIA began to win academic image-classification
competitions with GPU-trained deep neural networks—the first practical success of
modern deep learning. But the watershed moment came in 2012, with the entry of
Hinton’s group in the yearly large-scale image-classification challenge ImageNet. The
ImageNet challenge was notoriously difficult at the time, consisting of classifying
high-resolution color images into 1,000 different categories after training on 1.4 million
images. In 2011, the top-five accuracy of the winning model, based on classical
approaches to computer vision, was only 74.3%. Then, in 2012, a team led by Alex
Krizhevsky and advised by Geoffrey Hinton was able to achieve a top-five accuracy of
83.6%--a significant breakthrough. The competition has been dominated by deep
convolutional neural networks every year since. By 2015, the winner reached an accuracy
of 96.4%, and the classification task on ImageNet was considered to be a completely
solved problem.
Since 2012, deep convolutional neural networks (convnets) have become the go-to
algorithm for all computer vision tasks; more generally, they work on all perceptual
tasks. At major computer vision conferences in 2015 and 2016, it was nearly impossible
to find presentations that didn’t involve convnets in some form. At the same time, deep
learning has also found applications in many other types of problems, such as natural
language processing. It has completely replaced SVMs and decision trees in a wide range
of applications. For instance, for several years, the European Organization for Nuclear
Research, CERN, used decision tree–based methods for analysis of particle data from the
ATLAS detector at the Large Hadron Collider (LHC); but CERN eventually switched to
Keras-based deep neural networks due to their higher performance and ease of training
on large datasets.

1.2.6 What makes deep learning different

The primary reason deep learning took off so quickly is that it offered better performance
on many problems. But that’s not the only reason. Deep learning also makes
problem-solving much easier, because it completely automates what used to be the most
crucial step in a machine-learning workflow: feature engineering.
Previous machine-learning techniques—shallow learning—only involved
transforming the input data into one or two successive representation spaces, usually via
simple transformations such as high-dimensional non-linear projections (SVM) or
decision trees. But the refined representations required by complex problems generally
can’t be attained by such techniques. As such, humans had to go to great length to make
the initial input data more amenable to processing by these methods: that is, they had to
©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
17

manually engineer good layers of representations for their data. This is called feature
engineering. Deep learning, on the other hand, completely automates this step: with deep
learning, you learn all features in one pass rather than having to engineer them yourself.
This has greatly simplified machine-learning workflows, often replacing sophisticated
multistage pipelines with a single, simple, end-to-end deep-learning model.
You may ask, if the crux of the issue is to have multiple successive layers of
representation, could shallow methods be applied repeatedly to emulate the effects of
deep learning? In practice, there are fast-diminishing returns to successive applications of
shallow-learning methods, because the optimal first representation layer in a three-layer
model isn’t the optimal first layer in a one-layer or two-layer model . What is
transformative about deep learning is that it allows a model to learn all layers of
representation jointly, at the same time, rather than in succession (greedily, as it’s called).
With joint feature learning, whenever the model adjusts one of its internal features, all
other features that depend on it automatically adapt to the change, without requiring
human intervention. Everything is supervised by a single feedback signal: every change
in the model serves the end goal. This is much more powerful than greedily stacking
shallow models, because it allows for complex, abstract representations to be learned by
breaking them down into long series of intermediate spaces (layers); each space is only a
simple transformation away from the previous one.
These are the two essential characteristics of how deep learning learns from data: the
incremental, layer-by-layer way in which increasingly complex representations are
developed, and the fact these intermediate incremental representations are learned
jointly, each layer being updated to follow both the representational needs of the layer
above and the needs of the layer below. Together, these two properties have made deep
learning vastly more successful than previous approaches to machine learning.

1.2.7 The modern machine-learning landscape

A great way to get a sense of the current landscape of machine-learning algorithms and
tools is to look at machine-learning competitions on Kaggle. Due to its highly
competitive environment (some contests have thousands of entrants and million-dollar
prizes) and to the wide variety of machine-learning problems covered, Kaggle offers a
realistic way to assess what works and what doesn’t. So, what kind of algorithm is
reliably winning competitions? What tools do top entrants use?
In 2016, Kaggle was dominated by two approaches: gradient boosting machines and
deep learning. Specifically, gradient boosting is used for problems where structured data
is available, whereas deep learning is used for perceptual problems such as image
classification. Practitioners of the former almost always use the excellent XGBoost
library. Meanwhile, most of the Kaggle entrants leveraging deep learning use the Keras
library, due to its ease of use and flexibility. XGBoost and Keras both support the two
most popular data science languages: R and Python.
These are the two techniques you should be the most familiar with in order to be
successful in applied machine learning today: gradient boosting machines, for
©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
18

shallow-learning problems; and deep learning, for perceptual problems. In technical

terms, this means you’ll need to be familiar with XGB and Keras—the two libraries that
currently dominate Kaggle competitions. With this book in hand, you’re already one big
step closer.

1.3 Why deep learning? Why now?

The two key ideas of deep learning for computer vision—convolutional neural networks
and backpropagation—were already well understood in 1989. The Long Short-Term
Memory (LSTM) algorithm, which is fundamental to deep learning for time series, was
developed in 1997 and has barely changed since. So why did deep learning only take off
after 2012? What changed in these two decades?
In general, three technical forces are driving advances in machine learning:

Hardware
Datasets and benchmarks
Algorithmic advances

Because the field is guided by experimental findings rather than by theory,

algorithmic advances only become possible when appropriate data and hardware were
available to try new ideas (or scale up old ideas, as is often the case). Machine learning
isn’t mathematics or physics, where major advances can be done with a pen and a piece
of paper. It’s an engineering science.
The real bottlenecks throughout the 1990s and 2000s were data and hardware. But
here’s what happened during that time: the internet took off, and high-performance
graphics chips were developed for the needs of the gaming market.

1.3.1 Hardware
Between 1990 and 2010, off-the-shelf CPUs became faster by a factor of approximately
5,000. As a result, nowadays it’s possible to run small deep learning models on your
laptop, whereas this would have been intractable 25 years ago.
But typical deep-learning models used in computer vision or speech recognition
require orders of magnitude more computational power than what your laptop can
deliver. Throughout the 2000s, companies like NVIDIA and AMD have been investing
billions of dollars in developing fast, massively parallel chips (graphical processing units
[GPUs]) to power the graphics of increasingly photorealistic video games—cheap,
single-purpose supercomputers designed to render complex 3D scenes on your screen in
real time. This investment came to benefit the scientific community when, in 2007,
NVIDIA launched CUDA (developer.nvidia.com/about-cuda), a programming interface
for its line of GPUs. A small number of GPUs started replacing massive clusters of CPUs
in various highly parallelizable applications, beginning with physics modeling. Deep
neural networks, consisting mostly of many small matrix multiplications, are also highly

parallelizable; and around 2011, some researchers began to write CUDA

implementations of neural nets—Dan Ciresan4 and Alex Krizhevsky5 were among the
first.
Footnote 4mSee "Flexible, High Performance Convolutional Neural Networks for Image Classification,"
Proceedings of the 22nd International Joint Conference on Artificial Intelligence (2011),
www.ijcai.org/Proceedings/11/Papers/210.pdf.

Footnote 5mSee "ImageNet Classification with Deep Convolutional Neural Networks," Advances in
Neural Information Processing Systems 25 (2012), mng.bz/2286.

What happened is that the gaming market subsidized supercomputing for the next
generation of artificial intelligence applications. Sometimes, big things begin as games.
Today, the NVIDIA Titan X, a gaming GPU that cost $1,000 at the end of 2015, can
deliver a peak of 6.6 TLOPS in single precision: that is, 6.6 trillion float32 operations
per second. That’s about 350 times more than what you can get out of a modern laptop.
On a Titan X, it takes only a couple of days to train an ImageNet model of the sort that
would have won the ILSVRC competition a few years ago. Meanwhile, large companies
train deep-learning models on clusters of hundreds of GPUs of a type developed
specifically for the needs of deep learning, such as the NVIDIA K80. The sheer
computational power of such clusters is something that would never have been possible
without modern GPUs.
What’s more, the deep-learning industry is starting to go beyond GPUs and is
investing in increasingly specialized, efficient chips for deep learning. In 2016, at its
annual I/O convention, Google revealed its tensor processing unit (TPU) project: a new
chip design developed from the ground up to run deep neural networks, which is
reportedly 10 times faster and far more energy efficient than top-of-line GPUs.

1.3.2 Data
AI is sometimes heralded as the new industrial revolution. If deep learning is the steam
engine of this revolution, then data is its coal: the raw material that powers our intelligent
machines, without which nothing would be possible. When it comes to data, in addition
to the exponential progress in storage hardware over the past 20 years (following
Moore’s law), the game changer has been the rise of the internet, making it feasible to
collect and distribute very large datasets for machine learning. Today, large companies
work with image datasets, video datasets, and natural-language datasets that couldn’t
have been collected without the internet. User-generated image tags on Flickr, for
instance, have been a treasure trove of data for computer vision. So are YouTube videos.
And Wikipedia is a key dataset for natural-language processing.
If there’s one dataset that has been a catalyst for the rise of deep learning, it’s the
ImageNet dataset, consisting of 1.4 million images that have been hand-annotated with
1,000 image categories (1 category per image). But what makes ImageNet special isn’t
just its large size, but also the yearly competition associated with it.6

Footnote 6mThe ImageNet Large Scale Visual Recognition Challenge (ILSVRC),

www.image-net.org/challenges/LSVRC.

As Kaggle has been demonstrating since 2010, public competitions are an excellent
way to motivate researchers and engineers to push the envelope. Having common
benchmarks that researchers compete to beat has greatly helped the recent rise of deep
learning.

1.3.3 Algorithms
In addition to hardware and data, until the late 2000s, we were missing a reliable way to
train very deep neural networks. As a result, neural networks were still fairly shallow,
using only one or two layers of representations; thus they weren’t able to shine against
more refined shallow methods such as SVMs and random forests. The key issue was that
of gradient propagation through deep stacks of layers. The feedback signal used to train
neural networks would fade away as the number of layers increased.
This changed around 2009–2010 with the advent of several simple but important
algorithmic improvements that allowed for better gradient propagation:

Better activation functions for neural layers

Better weight-initialization schemes, starting with layer-wise pretraining, which was
quickly abandoned
Better optimization schemes, such as RMSProp and Adam

Only when these improvements began to allow for training models with 10 or more
layers did deep learning start to shine.
Finally, in 2014, 2015, and 2016, even more advanced ways to help gradient
propagation were discovered, such as batch normalization, residual connections, and
depthwise separable convolutions. Today we can train from scratch models that are
thousands of layers deep.

1.3.4 A new wave of investment

As deep learning became the new state of the art for computer vision in 2012–2013, and
eventually for all perceptual tasks, industry leaders took note. What followed was a
gradual wave of industry investment far beyond anything previously seen in the history
of AI.
In 2011, right before deep learning took the spotlight, the total venture capital
investment in AI was around $19 million, which went almost entirely to practical
applications of shallow machine-learning approaches. By 2014, it had risen to a
staggering $394 million. Dozens of startups launched in these three years, trying to
capitalize on the deep-learning hype. Meanwhile, large tech companies such as Google,
Facebook, Baidu, and Microsoft have invested in internal research departments in
amounts that would most likely dwarf the flow of venture-capital money. Only a few
numbers have surfaced: in 2013, Google acquired the deep-learning startup DeepMind
for a reported $500 million—the largest acquisition of an AI company in history. In

2014, Baidu started a deep-learning research center in Silicon Valley, investing $300
million in the project. The deep-learning hardware startup Nervana Systems was acquired
by Intel in 2016 for over $400 million.
Machine learning—in particular, deep learning—has become central to the product
strategy of these tech giants. In late 2015, Google CEO Sundar Pichai stated, "Machine
learning is a core, transformative way by which we’re rethinking how we’re doing
everything. We’re thoughtfully applying it across all our products, be it search, ads,
YouTube, or Play. And we’re in early days, but you’ll see us—in a systematic
way—apply machine learning in all these areas."
As a result of this wave of investment, the number of people working on deep
learning went in just five years from a few hundred to tens of thousands, and research
progress has reached a frenetic pace. There are currently no signs that this trend will slow
any time soon.

1.3.5 The democratization of deep learning

One the key factors driving this inflow of new faces in deep learning has been the
democratization of the toolsets used in the field. In the early days, doing deep learning
required significant C++ and CUDA expertise, which few people possessed. Nowadays,
basic Python or R scripting skills suffice to do advanced deep-learning research. This has
been driven most notably by the development of Theano and then TensorFlow—two
symbolic tensor-manipulation frameworks that support auto-differentiation, greatly
simplifying the implementation of new models—and by the rise of user-friendly libraries
such as Keras, which makes deep learning as easy as manipulating LEGO bricks. After
its release early 2015, Keras quickly became the go-to deep-learning solution for large
numbers of new startups, grad students, and researchers pivoting into the field.

1.3.6 Will it last?

Is there anything special about deep neural networks that makes them the "right"
approach for companies to be investing in and for researchers to flock to? Or is deep
learning just a fad that may not last? Will we still be using deep neural networks in 20
years?
The short answer is yes—deep learning has several properties that justify its status as
an AI revolution, and it’s here to stay. We may not be using neural networks two decades
from now, but whatever we use will directly inherit from modern deep learning and its
core concepts. These important properties can be broadly sorted into three categories:

Simplicity—Deep learning removes the need for feature engineering, replacing complex,
brittle, engineering-heavy pipelines with simple, end-to-end trainable models that are
typically built using only five or six different tensor operations.
Scalability—Deep learning is highly amenable to parallelization on GPUs or TPUs, so it
can take full advantage of Moore’s law. In addition, deep-learning models are trained by
iterating over small batches of data, allowing them to be trained on datasets of arbitrary
size. (The only bottleneck is the amount of parallel computational power available,
which, thanks to Moore’s law, is a fast-moving barrier.)
Versatility and reusability—Unlike many prior machine-learning approaches,
©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
22

deep-learning models can be trained on additional data without restarting from scratch,
making them viable for continuous online learning—an important property for very large
production models. Furthermore, trained deep-learning models are repurposable and thus
reusable: for instance, it’s possible to take a deep-learning model trained for image
classification and drop it into a video-processing pipeline. This allows us to reinvest
previous work into increasingly complex and powerful models. This also makes deep
learning applicable to fairly small datasets.

Deep learning has only been in the spotlight for a few years, and we haven’t yet
established the full scope of what it can do. With every passing month, we learn about
new use cases and engineering improvements that lift previous limitations. Following a
scientific revolution, progress generally follows a sigmoid curve: it starts with a period of
fast progress, which gradually stabilizes as researchers hit hard limitations, and then
further improvements become incremental. Deep learning in 2017 seems to be in the first
half of that sigmoid, with much more progress to come in the next few years.

Before we begin: the mathematical

blocks of neural networks

This chapter covers

A first example of a neural network

2
Tensors and tensor operations
How neural networks learn, via backpropagation and gradient descent

Understanding deep learning requires familiarity with many simple mathematical

concepts: tensors, tensor operations, differentiation, gradient descent, and so on. Our goal
in this chapter will be to build your intuition about these notions without getting overly
technical. In particular, we’ll steer away from mathematical notation, which can be
off-putting for those without any mathematics background and isn’t strictly necessary to
explain things well.
To add some context for tensors and gradient descent, we’ll begin the chapter with a
practical example of a neural network. Then we’ll go over every new concept that’s been
introduced, point by point. Keep in mind that these concepts will be essential for you to
understand the practical examples that will come in the following chapters!
After reading this chapter, you’ll have an intuitive understanding of how neural
networks work, and you’ll be able to move on to practical applications—which will start
with chapter 3.

2.1 A first look at a neural network

Let’s look at a concrete example of a neural network that uses the Keras R package to
learn to classify hand-written digits. Unless you already have experience with Keras or
similar libraries, you will not understand everything about this first example right away.
You probably haven’t even installed Keras yet. Don’t worry, that is perfectly fine. In the
next chapter, we will review each element in our example and explain them in detail. So
don’t worry if some steps seem arbitrary or look like magic to you! We’ve got to start
somewhere.
The problem we’re trying to solve here is to classify grayscale images of handwritten
digits (28 pixels by 28 pixels) into their 10 categories (0 to 9). We’ll use the MNIST
©Manning Publications Co. We welcome reader comments about anything in the manuscript - other than typos and
other simple mistakes. These will be cleaned up during production of the book by copyeditors and proofreaders.
https://forums.manning.com/forums/deep-learning-with-r
Estadísticos e-Books & Papers Licensed to <null> Estadísticos e-Books & Papers
24

dataset, a classic dataset in the machine-learning community, which has been around
almost as long as the field itself and has been intensively studied. It’s a set of 60,000
training images, plus 10,000 test images, assembled by the National Institute of
Standards and Technology (the NIST in MNIST) in the 1980s. You can think of
"solving" MNIST as the "Hello World" of deep learning—it’s what you do to verify that
your algorithms are working as expected. As you become a machine- learning
practitioner, you’ll see MNIST come up over and over again, in scientific papers, blog
posts, and so on. You can see some MNIST samples in figure 2.1.

SIDEBAR Note on classes and labels

In machine learning, a category in a classification problem is called a class.
Data points are called samples. The class associated with a specific sample
is called a label.

Figure 2.1 MNIST sample digits

You don’t need to try to reproduce this example on your machine just now. If you
wish to, you’ll first need to set up Keras, which is covered in section 3.3.
The MNIST dataset comes preloaded in Keras, in the form of train and test lists,
each of which includes a set of images (x) and associated labels (y):

Listing 2.1 Loading the MNIST dataset in Keras

library(keras)

mnist <- dataset_mnist()

train_images <- mnist$train$x
train_labels <- mnist$train$y
test_images <- mnist$test$x
test_labels <- mnist$test$y

train_images and train_labels form the training set, the data that the model will
learn from. The model will then be tested on the test set, test_images and test_labels
. The images are encoded as as 3D arrays, and the labels are a 1D array of digits, ranging
from 0 to 9. There is a one-to-one correspondence between the images and the labels.
The R str() function is a convenient way to get a quick glimpse at the structure of
an array. Let’s use it to have a look at the training data:

> str(train_images)
int [1:60000, 1:28, 1:28] 0 0 0 0 0 0 0 0 0 0 ...
> str(train_labels)
int [1:60000(1d)] 5 0 4 1 9 2 1 3 1 4 ...

And here’s the test data:

> str(test_images)
int [1:10000, 1:28, 1:28] 0 0 0 0 0 0 0 0 0 0 ...
> str(test_labels)
int [1:10000(1d)] 7 2 1 0 4 1 4 9 5 9 ...

The workflow will be as follows: first we’ll feed the neural network the training data,
train_images and train_labels. The network will then learn to associate images and
labels. Finally, we’ll ask the network to produce predictions for test_images, and we’ll
verify whether these predictions match the labels from test_labels.
Let’s build the network—again, remember that you aren’t supposed to understand
everything about this example yet.

Listing 2.2 The network architecture

network <- keras_model_sequential() %>%

layer_dense(units = 512, activation = "relu", input_shape = c(28 * 28)) %>%
layer_dense(units = 10, activation = "softmax")

If you aren’t familliar with the pipe (%>%) operator used to invoke methods on the
network object fear not, we’ll cover this when we review this example again towards the
end of this chapter. For now, read it in your head as "then" (e.g. start with a model, then
add a layer, then add another layer, etc.).
The core building block of neural networks is the layer, a data-processing module that
you can think of as a filter for data. Some data comes in, and it comes out in a more
useful form. Specifically, layers extract representations out of the data fed into
them—hopefully representations that are more meaningful for the problem at hand. Most
of deep learning consists of chaining together simple layers that will implement a form of
progressive data distillation. A deep-learning model is like a sieve for data processing,
made of a succession of increasingly refined data filters—the layers.
Here our network consists of a sequence of two layers, which are densely connected
(also called fully connected) neural layers. The second (and last) layer is a 10-way
softmax layer, which means it will return an array of 10 probability scores (summing to
1). Each score will be the probability that the current digit image belongs to one of our 10
digit classes.
To make the network ready for training, we need to pick three more things, as part of
the compilation step:

A loss function—How the network will be able to measure how good a job it’s doing on
its training data, and thus how it will be able to steer itself in the right direction.
An optimizer—The mechanism through which the network will update itself based on the
data it sees and its loss function.
Metrics to monitor during training and testing—Here we’ll only care about accuracy (the
fraction of the images that were correctly classified).

The exact purpose of the loss function and the optimizer will be made clear

STREET & SMITH CORPORATION

79 Seventh Avenue New York
City
Transcriber’s Notes:
Punctuation has been made consistent.
Variations in spelling and hyphenation were retained as they appear in the original
publication, except that obvious typographical errors have been corrected.
The following change was made:
p. 100: its changed to his (leaning his weight)
*** END OF THE PROJECT GUTENBERG EBOOK LOVE'S LABOR
WON ***

Updated editions will replace the previous one—the old editions

will be renamed.

Creating the works from print editions not protected by U.S.

copyright law means that no one owns a United States copyright
in these works, so the Foundation (and you!) can copy and
distribute it in the United States without permission and without
paying copyright royalties. Special rules, set forth in the General
Terms of Use part of this license, apply to copying and
distributing Project Gutenberg™ electronic works to protect the
PROJECT GUTENBERG™ concept and trademark. Project
Gutenberg is a registered trademark, and may not be used if
you charge for an eBook, except by following the terms of the
trademark license, including paying royalties for use of the
Project Gutenberg trademark. If you do not charge anything for
copies of this eBook, complying with the trademark license is
very easy. You may use this eBook for nearly any purpose such
as creation of derivative works, reports, performances and
research. Project Gutenberg eBooks may be modified and
printed and given away—you may do practically ANYTHING in
the United States with eBooks not protected by U.S. copyright
law. Redistribution is subject to the trademark license, especially
commercial redistribution.

START: FULL LICENSE

THE FULL PROJECT GUTENBERG LICENSE
PLEASE READ THIS BEFORE YOU DISTRIBUTE OR USE THIS WORK

To protect the Project Gutenberg™ mission of promoting the

free distribution of electronic works, by using or distributing this
work (or any other work associated in any way with the phrase
“Project Gutenberg”), you agree to comply with all the terms of
the Full Project Gutenberg™ License available with this file or
online at www.gutenberg.org/license.

Section 1. General Terms of Use and

Redistributing Project Gutenberg™
electronic works
1.A. By reading or using any part of this Project Gutenberg™
electronic work, you indicate that you have read, understand,
agree to and accept all the terms of this license and intellectual
property (trademark/copyright) agreement. If you do not agree to
abide by all the terms of this agreement, you must cease using
and return or destroy all copies of Project Gutenberg™
electronic works in your possession. If you paid a fee for
obtaining a copy of or access to a Project Gutenberg™
electronic work and you do not agree to be bound by the terms
of this agreement, you may obtain a refund from the person or
entity to whom you paid the fee as set forth in paragraph 1.E.8.

1.B. “Project Gutenberg” is a registered trademark. It may only

be used on or associated in any way with an electronic work by
people who agree to be bound by the terms of this agreement.
There are a few things that you can do with most Project
Gutenberg™ electronic works even without complying with the
full terms of this agreement. See paragraph 1.C below. There
are a lot of things you can do with Project Gutenberg™
electronic works if you follow the terms of this agreement and
help preserve free future access to Project Gutenberg™
electronic works. See paragraph 1.E below.
1.C. The Project Gutenberg Literary Archive Foundation (“the
Foundation” or PGLAF), owns a compilation copyright in the
collection of Project Gutenberg™ electronic works. Nearly all the
individual works in the collection are in the public domain in the
United States. If an individual work is unprotected by copyright
law in the United States and you are located in the United
States, we do not claim a right to prevent you from copying,
distributing, performing, displaying or creating derivative works
based on the work as long as all references to Project
Gutenberg are removed. Of course, we hope that you will
support the Project Gutenberg™ mission of promoting free
access to electronic works by freely sharing Project
Gutenberg™ works in compliance with the terms of this
agreement for keeping the Project Gutenberg™ name
associated with the work. You can easily comply with the terms
of this agreement by keeping this work in the same format with
its attached full Project Gutenberg™ License when you share it
without charge with others.

1.D. The copyright laws of the place where you are located also
govern what you can do with this work. Copyright laws in most
countries are in a constant state of change. If you are outside
the United States, check the laws of your country in addition to
the terms of this agreement before downloading, copying,
displaying, performing, distributing or creating derivative works
based on this work or any other Project Gutenberg™ work. The
Foundation makes no representations concerning the copyright
status of any work in any country other than the United States.

1.E. Unless you have removed all references to Project

Gutenberg:

1.E.1. The following sentence, with active links to, or other

immediate access to, the full Project Gutenberg™ License must
appear prominently whenever any copy of a Project
Gutenberg™ work (any work on which the phrase “Project
Gutenberg” appears, or with which the phrase “Project
Gutenberg” is associated) is accessed, displayed, performed,
viewed, copied or distributed:

This eBook is for the use of anyone anywhere in the United

States and most other parts of the world at no cost and with
almost no restrictions whatsoever. You may copy it, give it
away or re-use it under the terms of the Project Gutenberg
License included with this eBook or online at
www.gutenberg.org. If you are not located in the United
States, you will have to check the laws of the country where
you are located before using this eBook.

1.E.2. If an individual Project Gutenberg™ electronic work is

derived from texts not protected by U.S. copyright law (does not
contain a notice indicating that it is posted with permission of the
copyright holder), the work can be copied and distributed to
anyone in the United States without paying any fees or charges.
If you are redistributing or providing access to a work with the
phrase “Project Gutenberg” associated with or appearing on the
work, you must comply either with the requirements of
paragraphs 1.E.1 through 1.E.7 or obtain permission for the use
of the work and the Project Gutenberg™ trademark as set forth
in paragraphs 1.E.8 or 1.E.9.

1.E.3. If an individual Project Gutenberg™ electronic work is

posted with the permission of the copyright holder, your use and
distribution must comply with both paragraphs 1.E.1 through
1.E.7 and any additional terms imposed by the copyright holder.
Additional terms will be linked to the Project Gutenberg™
License for all works posted with the permission of the copyright
holder found at the beginning of this work.

1.E.4. Do not unlink or detach or remove the full Project

Gutenberg™ License terms from this work, or any files
containing a part of this work or any other work associated with
Project Gutenberg™.
1.E.5. Do not copy, display, perform, distribute or redistribute
this electronic work, or any part of this electronic work, without
prominently displaying the sentence set forth in paragraph 1.E.1
with active links or immediate access to the full terms of the
Project Gutenberg™ License.

1.E.6. You may convert to and distribute this work in any binary,
compressed, marked up, nonproprietary or proprietary form,
including any word processing or hypertext form. However, if
you provide access to or distribute copies of a Project
Gutenberg™ work in a format other than “Plain Vanilla ASCII” or
other format used in the official version posted on the official
Project Gutenberg™ website (www.gutenberg.org), you must, at
no additional cost, fee or expense to the user, provide a copy, a
means of exporting a copy, or a means of obtaining a copy upon
request, of the work in its original “Plain Vanilla ASCII” or other
form. Any alternate format must include the full Project
Gutenberg™ License as specified in paragraph 1.E.1.

1.E.7. Do not charge a fee for access to, viewing, displaying,

performing, copying or distributing any Project Gutenberg™
works unless you comply with paragraph 1.E.8 or 1.E.9.

1.E.8. You may charge a reasonable fee for copies of or

providing access to or distributing Project Gutenberg™
electronic works provided that:

• You pay a royalty fee of 20% of the gross profits you derive from
the use of Project Gutenberg™ works calculated using the
method you already use to calculate your applicable taxes. The
fee is owed to the owner of the Project Gutenberg™ trademark,
but he has agreed to donate royalties under this paragraph to
the Project Gutenberg Literary Archive Foundation. Royalty
payments must be paid within 60 days following each date on
which you prepare (or are legally required to prepare) your
periodic tax returns. Royalty payments should be clearly marked
as such and sent to the Project Gutenberg Literary Archive
Foundation at the address specified in Section 4, “Information
about donations to the Project Gutenberg Literary Archive
Foundation.”

• You provide a full refund of any money paid by a user who

notifies you in writing (or by e-mail) within 30 days of receipt that
s/he does not agree to the terms of the full Project Gutenberg™
License. You must require such a user to return or destroy all
copies of the works possessed in a physical medium and
discontinue all use of and all access to other copies of Project
Gutenberg™ works.

• You provide, in accordance with paragraph 1.F.3, a full refund of

any money paid for a work or a replacement copy, if a defect in
the electronic work is discovered and reported to you within 90
days of receipt of the work.

• You comply with all other terms of this agreement for free
distribution of Project Gutenberg™ works.

1.E.9. If you wish to charge a fee or distribute a Project

Gutenberg™ electronic work or group of works on different
terms than are set forth in this agreement, you must obtain
permission in writing from the Project Gutenberg Literary
Archive Foundation, the manager of the Project Gutenberg™
trademark. Contact the Foundation as set forth in Section 3
below.

1.F.

1.F.1. Project Gutenberg volunteers and employees expend

considerable effort to identify, do copyright research on,
transcribe and proofread works not protected by U.S. copyright
law in creating the Project Gutenberg™ collection. Despite
these efforts, Project Gutenberg™ electronic works, and the
medium on which they may be stored, may contain “Defects,”
such as, but not limited to, incomplete, inaccurate or corrupt
data, transcription errors, a copyright or other intellectual
property infringement, a defective or damaged disk or other
medium, a computer virus, or computer codes that damage or
cannot be read by your equipment.

1.F.2. LIMITED WARRANTY, DISCLAIMER OF DAMAGES -

Except for the “Right of Replacement or Refund” described in
paragraph 1.F.3, the Project Gutenberg Literary Archive
Foundation, the owner of the Project Gutenberg™ trademark,
and any other party distributing a Project Gutenberg™ electronic
work under this agreement, disclaim all liability to you for
damages, costs and expenses, including legal fees. YOU
AGREE THAT YOU HAVE NO REMEDIES FOR NEGLIGENCE,
STRICT LIABILITY, BREACH OF WARRANTY OR BREACH
OF CONTRACT EXCEPT THOSE PROVIDED IN PARAGRAPH
1.F.3. YOU AGREE THAT THE FOUNDATION, THE
TRADEMARK OWNER, AND ANY DISTRIBUTOR UNDER
THIS AGREEMENT WILL NOT BE LIABLE TO YOU FOR
ACTUAL, DIRECT, INDIRECT, CONSEQUENTIAL, PUNITIVE
OR INCIDENTAL DAMAGES EVEN IF YOU GIVE NOTICE OF
THE POSSIBILITY OF SUCH DAMAGE.

1.F.3. LIMITED RIGHT OF REPLACEMENT OR REFUND - If

you discover a defect in this electronic work within 90 days of
receiving it, you can receive a refund of the money (if any) you
paid for it by sending a written explanation to the person you
received the work from. If you received the work on a physical
medium, you must return the medium with your written
explanation. The person or entity that provided you with the
defective work may elect to provide a replacement copy in lieu
of a refund. If you received the work electronically, the person or
entity providing it to you may choose to give you a second
opportunity to receive the work electronically in lieu of a refund.
If the second copy is also defective, you may demand a refund
in writing without further opportunities to fix the problem.

1.F.4. Except for the limited right of replacement or refund set

forth in paragraph 1.F.3, this work is provided to you ‘AS-IS’,
WITH NO OTHER WARRANTIES OF ANY KIND, EXPRESS
OR IMPLIED, INCLUDING BUT NOT LIMITED TO
WARRANTIES OF MERCHANTABILITY OR FITNESS FOR
ANY PURPOSE.

1.F.5. Some states do not allow disclaimers of certain implied

warranties or the exclusion or limitation of certain types of
damages. If any disclaimer or limitation set forth in this
agreement violates the law of the state applicable to this
agreement, the agreement shall be interpreted to make the
maximum disclaimer or limitation permitted by the applicable
state law. The invalidity or unenforceability of any provision of
this agreement shall not void the remaining provisions.

1.F.6. INDEMNITY - You agree to indemnify and hold the

Foundation, the trademark owner, any agent or employee of the
Foundation, anyone providing copies of Project Gutenberg™
electronic works in accordance with this agreement, and any
volunteers associated with the production, promotion and
distribution of Project Gutenberg™ electronic works, harmless
from all liability, costs and expenses, including legal fees, that
arise directly or indirectly from any of the following which you do
or cause to occur: (a) distribution of this or any Project
Gutenberg™ work, (b) alteration, modification, or additions or
deletions to any Project Gutenberg™ work, and (c) any Defect
you cause.

Section 2. Information about the Mission of

Project Gutenberg™
Project Gutenberg™ is synonymous with the free distribution of
electronic works in formats readable by the widest variety of
computers including obsolete, old, middle-aged and new
computers. It exists because of the efforts of hundreds of
volunteers and donations from people in all walks of life.

Volunteers and financial support to provide volunteers with the

assistance they need are critical to reaching Project
Gutenberg™’s goals and ensuring that the Project Gutenberg™
collection will remain freely available for generations to come. In
2001, the Project Gutenberg Literary Archive Foundation was
created to provide a secure and permanent future for Project
Gutenberg™ and future generations. To learn more about the
Project Gutenberg Literary Archive Foundation and how your
efforts and donations can help, see Sections 3 and 4 and the
Foundation information page at www.gutenberg.org.

Section 3. Information about the Project

Gutenberg Literary Archive Foundation
The Project Gutenberg Literary Archive Foundation is a non-
profit 501(c)(3) educational corporation organized under the
laws of the state of Mississippi and granted tax exempt status by
the Internal Revenue Service. The Foundation’s EIN or federal
tax identification number is 64-6221541. Contributions to the
Project Gutenberg Literary Archive Foundation are tax
deductible to the full extent permitted by U.S. federal laws and
your state’s laws.

The Foundation’s business office is located at 809 North 1500

West, Salt Lake City, UT 84116, (801) 596-1887. Email contact
links and up to date contact information can be found at the
Foundation’s website and official page at
www.gutenberg.org/contact

Section 4. Information about Donations to

the Project Gutenberg Literary Archive
Foundation
Project Gutenberg™ depends upon and cannot survive without
widespread public support and donations to carry out its mission
of increasing the number of public domain and licensed works
that can be freely distributed in machine-readable form
accessible by the widest array of equipment including outdated
equipment. Many small donations ($1 to $5,000) are particularly
important to maintaining tax exempt status with the IRS.

The Foundation is committed to complying with the laws

regulating charities and charitable donations in all 50 states of
the United States. Compliance requirements are not uniform
and it takes a considerable effort, much paperwork and many
fees to meet and keep up with these requirements. We do not
solicit donations in locations where we have not received written
confirmation of compliance. To SEND DONATIONS or
determine the status of compliance for any particular state visit
www.gutenberg.org/donate.

While we cannot and do not solicit contributions from states

where we have not met the solicitation requirements, we know
of no prohibition against accepting unsolicited donations from
donors in such states who approach us with offers to donate.

International donations are gratefully accepted, but we cannot

make any statements concerning tax treatment of donations
received from outside the United States. U.S. laws alone swamp
our small staff.

Please check the Project Gutenberg web pages for current

donation methods and addresses. Donations are accepted in a
number of other ways including checks, online payments and
credit card donations. To donate, please visit:
www.gutenberg.org/donate.

Section 5. General Information About Project

Gutenberg™ electronic works
Professor Michael S. Hart was the originator of the Project
Gutenberg™ concept of a library of electronic works that could
be freely shared with anyone. For forty years, he produced and
distributed Project Gutenberg™ eBooks with only a loose
network of volunteer support.

Project Gutenberg™ eBooks are often created from several

printed editions, all of which are confirmed as not protected by
copyright in the U.S. unless a copyright notice is included. Thus,
we do not necessarily keep eBooks in compliance with any
particular paper edition.

Most people start at our website which has the main PG search
facility: www.gutenberg.org.

This website includes information about Project Gutenberg™,

including how to make donations to the Project Gutenberg
Literary Archive Foundation, how to help produce our new
eBooks, and how to subscribe to our email newsletter to hear
about new eBooks.
Welcome to our website – the ideal destination for book lovers and
knowledge seekers. With a mission to inspire endlessly, we offer a
vast collection of books, ranging from classic literary works to
specialized publications, self-development books, and children's
literature. Each book is a new journey of discovery, expanding
knowledge and enriching the soul of the reade

Our website is not just a platform for buying books, but a bridge
connecting readers to the timeless values of culture and wisdom. With
an elegant, user-friendly interface and an intelligent search system,
we are committed to providing a quick and convenient shopping
experience. Additionally, our special promotions and home delivery
services ensure that you save time and fully enjoy the joy of reading.

Let us accompany you on the journey of exploring knowledge and

personal growth!

textbookfull.com

Instant download (Ebook) Deep Learning with R by François Chollet, J.J. Allaire ISBN 9782541471266, 2541471262 pdf all chapter
100% (12)
Instant download (Ebook) Deep Learning with R by François Chollet, J.J. Allaire ISBN 9782541471266, 2541471262 pdf all chapter
67 pages
Matlab Deep Learning Series
No ratings yet
Matlab Deep Learning Series
6 pages
Machine Learning Full Question Bank
No ratings yet
Machine Learning Full Question Bank
14 pages
Dl Question Bank
No ratings yet
Dl Question Bank
23 pages
ML Unit-Iv
No ratings yet
ML Unit-Iv
19 pages
KNN Algorithm
No ratings yet
KNN Algorithm
3 pages
Answers For End-Sem Exam Part - 2 (Deep Learning)
No ratings yet
Answers For End-Sem Exam Part - 2 (Deep Learning)
20 pages
Lab I TENSOR FLOW AND KERAS
No ratings yet
Lab I TENSOR FLOW AND KERAS
3 pages
RAG with math
No ratings yet
RAG with math
7 pages
Deep Learning With Tensorflow
No ratings yet
Deep Learning With Tensorflow
15 pages
Autoencoders
No ratings yet
Autoencoders
66 pages
Deep Learning
No ratings yet
Deep Learning
2 pages
Deep Learning Step by Step
No ratings yet
Deep Learning Step by Step
171 pages
Dl All Units Materials
No ratings yet
Dl All Units Materials
138 pages
ML Lab
No ratings yet
ML Lab
21 pages
Core Java
No ratings yet
Core Java
217 pages
MACHINE LEARNING 1-5 (Ai &DS)
100% (1)
MACHINE LEARNING 1-5 (Ai &DS)
60 pages
Deep Learning Exp
No ratings yet
Deep Learning Exp
25 pages
DL Lab Manual
No ratings yet
DL Lab Manual
65 pages
Artificial Neural Networks: Part 1/3
No ratings yet
Artificial Neural Networks: Part 1/3
25 pages
SRM Valliammai Engineering College (An Autonomous Institution)
No ratings yet
SRM Valliammai Engineering College (An Autonomous Institution)
9 pages
1. Deep Learning
No ratings yet
1. Deep Learning
127 pages
ML Unit-2
No ratings yet
ML Unit-2
26 pages
Unit -3-NNDL- Notes
No ratings yet
Unit -3-NNDL- Notes
17 pages
Optimization Techniques in Deep Learning
No ratings yet
Optimization Techniques in Deep Learning
14 pages
Question Bank Module-1: Department of Computer Applications 18mca53 - Machine Learning
No ratings yet
Question Bank Module-1: Department of Computer Applications 18mca53 - Machine Learning
7 pages
Deep Learning Lab Practicals
No ratings yet
Deep Learning Lab Practicals
24 pages
RBM, DBN, and DBM
No ratings yet
RBM, DBN, and DBM
79 pages
Hyperparameters
No ratings yet
Hyperparameters
15 pages
50 Most Important CNN Interview Questions
No ratings yet
50 Most Important CNN Interview Questions
18 pages
Gradient Descent
No ratings yet
Gradient Descent
15 pages
Unit 2
No ratings yet
Unit 2
112 pages
SCSA3015 Deep Learning Unit 2 PDF
No ratings yet
SCSA3015 Deep Learning Unit 2 PDF
32 pages
Nueral Network Mcqs
No ratings yet
Nueral Network Mcqs
6 pages
Practice Final sp22
No ratings yet
Practice Final sp22
10 pages
Deep Learning 117 MCQ
No ratings yet
Deep Learning 117 MCQ
33 pages
Deep Learning Unit-1 Finals
No ratings yet
Deep Learning Unit-1 Finals
23 pages
2.building Blocks of Neural Networks
100% (1)
2.building Blocks of Neural Networks
2 pages
02 ML Supervised Learning
No ratings yet
02 ML Supervised Learning
32 pages
Module2.3 Hyperparameter Optimization
No ratings yet
Module2.3 Hyperparameter Optimization
29 pages
ML Question Bank 2024
No ratings yet
ML Question Bank 2024
2 pages
Machine Learning Notes
No ratings yet
Machine Learning Notes
3 pages
Deep Learning Question Bank(2024-25)
No ratings yet
Deep Learning Question Bank(2024-25)
2 pages
Chapter 06 Test Reviewer
No ratings yet
Chapter 06 Test Reviewer
5 pages
Tensor Flow
No ratings yet
Tensor Flow
12 pages
Machine Learning Module-3
No ratings yet
Machine Learning Module-3
23 pages
UNIT-4
No ratings yet
UNIT-4
79 pages
Query Operation 2021
No ratings yet
Query Operation 2021
35 pages
Unit-5 DS Notes
No ratings yet
Unit-5 DS Notes
19 pages
PPT_Btech CSE
No ratings yet
PPT_Btech CSE
17 pages
Lecture 26-30 Unit 2
No ratings yet
Lecture 26-30 Unit 2
20 pages
Deep Learning: Prof:Naveen Ghorpade
No ratings yet
Deep Learning: Prof:Naveen Ghorpade
43 pages
Machine Learning QB
No ratings yet
Machine Learning QB
3 pages
Prediction of Alzheimer's Disease Using CNN
100% (2)
Prediction of Alzheimer's Disease Using CNN
11 pages
Seminar Report Machine Learning
No ratings yet
Seminar Report Machine Learning
20 pages
Bidirectional RNN and RVNN
No ratings yet
Bidirectional RNN and RVNN
15 pages
CS3591 Computer Networks Lab manual finalized (3)
No ratings yet
CS3591 Computer Networks Lab manual finalized (3)
67 pages
Deep Learning Unit1
No ratings yet
Deep Learning Unit1
63 pages
ML Unit-4
No ratings yet
ML Unit-4
9 pages
Hebbian Learning: Fundamentals and Applications for Uniting Memory and Learning
From Everand
Hebbian Learning: Fundamentals and Applications for Uniting Memory and Learning
Fouad Sabry
No ratings yet
Buy ebook Wittgenstein s Family Letters Corresponding with Ludwig Brian Mcguinness cheap price
100% (1)
Buy ebook Wittgenstein s Family Letters Corresponding with Ludwig Brian Mcguinness cheap price
65 pages
Instant Access to Raspbian OS Programming with the Raspberry Pi: IoT Projects with Wolfram, Mathematica, and Scratch 1st Edition Agus Kurniawan ebook Full Chapters
100% (2)
Instant Access to Raspbian OS Programming with the Raspberry Pi: IoT Projects with Wolfram, Mathematica, and Scratch 1st Edition Agus Kurniawan ebook Full Chapters
55 pages
Download Full Site Characterization in Karst and Pseudokarst Terraines Practical Strategies and Technology for Practicing Engineers Hydrologists and Geologists 1st Edition Richard C. Benson PDF All Chapters
100% (2)
Download Full Site Characterization in Karst and Pseudokarst Terraines Practical Strategies and Technology for Practicing Engineers Hydrologists and Geologists 1st Edition Richard C. Benson PDF All Chapters
65 pages
Buy ebook Feast Fast or Famine Food and Drink in Byzantium Wendy Mayer cheap price
100% (2)
Buy ebook Feast Fast or Famine Food and Drink in Byzantium Wendy Mayer cheap price
55 pages
Instant Download Deep Learning Vol 2 From Basics to Practice Andrew Glassner PDF All Chapters
100% (2)
Instant Download Deep Learning Vol 2 From Basics to Practice Andrew Glassner PDF All Chapters
55 pages
Predictive Maintenance Using Deep Learning and Fre
No ratings yet
Predictive Maintenance Using Deep Learning and Fre
15 pages
DL 3
No ratings yet
DL 3
9 pages
Chapter 1 CYTED Book
No ratings yet
Chapter 1 CYTED Book
19 pages
Resume Sonaika Pati D (010824) - 4-1
No ratings yet
Resume Sonaika Pati D (010824) - 4-1
2 pages
Jpeodx Pveng-1194
No ratings yet
Jpeodx Pveng-1194
18 pages
DR Synopsis
No ratings yet
DR Synopsis
5 pages
Deep Ensemble Architectures With Heterogeneous Approach For An Efficient Content-Based Image Retrieval
No ratings yet
Deep Ensemble Architectures With Heterogeneous Approach For An Efficient Content-Based Image Retrieval
13 pages
Assignment 2
No ratings yet
Assignment 2
5 pages
Introduction To Responsible AI
No ratings yet
Introduction To Responsible AI
19 pages
Unit 4 Final
No ratings yet
Unit 4 Final
29 pages
Action n Pose Estimation
No ratings yet
Action n Pose Estimation
84 pages
Report On The Impact of Artificial Intelligence On Project Management
No ratings yet
Report On The Impact of Artificial Intelligence On Project Management
54 pages
Smita Yadavannavar
No ratings yet
Smita Yadavannavar
2 pages
Deep Learning - IIT Ropar - Unit 11 - Week 8
No ratings yet
Deep Learning - IIT Ropar - Unit 11 - Week 8
4 pages
Deep Learning Models For Plant Disease Detection and Diagnosis.
No ratings yet
Deep Learning Models For Plant Disease Detection and Diagnosis.
9 pages
Deep Learning-Based Prediction of Test Input Validity For RESTful APIs
No ratings yet
Deep Learning-Based Prediction of Test Input Validity For RESTful APIs
8 pages
Applications of Object Detection in
No ratings yet
Applications of Object Detection in
19 pages
Part B Unit 2 AI Project Cycle
No ratings yet
Part B Unit 2 AI Project Cycle
25 pages
Muhammad Azeem: Research Interests and Objectives
No ratings yet
Muhammad Azeem: Research Interests and Objectives
3 pages
UPDATED - HGDML - ALL QUIZ QUESTIONS and ANSWERS v2.3.1
100% (1)
UPDATED - HGDML - ALL QUIZ QUESTIONS and ANSWERS v2.3.1
15 pages
Hpca 2022
No ratings yet
Hpca 2022
15 pages
Applications of Game Theory in Deep Learning
No ratings yet
Applications of Game Theory in Deep Learning
93 pages
Chapter - 1
No ratings yet
Chapter - 1
33 pages
An Overview of Adversarial Attacks, Defenses
No ratings yet
An Overview of Adversarial Attacks, Defenses
29 pages
Artificial Intelligence Group No 1 Assignment 1
No ratings yet
Artificial Intelligence Group No 1 Assignment 1
5 pages
Lesson 1
No ratings yet
Lesson 1
37 pages
Real-Time Video Violence Detection Using CNN
No ratings yet
Real-Time Video Violence Detection Using CNN
7 pages
Face Mask Detection Using Python and Deep Learning
No ratings yet
Face Mask Detection Using Python and Deep Learning
16 pages
Neural Markov Random Field For Stereo Matching
No ratings yet
Neural Markov Random Field For Stereo Matching
13 pages
Chapter 5 Artificial Intelligence notes
No ratings yet
Chapter 5 Artificial Intelligence notes
7 pages