Scribd
Upload
3 views

Deep Learning and CNN

Uploaded by

basu.sap22
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
3 views

Deep Learning and CNN

Uploaded by

basu.sap22
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOCX, PDF, TXT or read online on Scribd
You are on page 1/ 38

-

Introduction to Deep Learning


Artificial Intelligence (AI), AIis intelligence demonstrated by
machines, as opposed to natural intelligence
Machine Learning (ML), displayed by animals including humans.

and Deep Learning (DL)


MLis the study of computer algorithms
that can improve automatically through
experience and using data. It is seen as a
part of artificial intelligence.

DLis part of a broader family of machine


learning methods based on artificial neural
networks.

( Source: Wikipedia
)
Relationship of AI, ML
and DL Artificial Intelligence

● Artificial Intelligence (AI)


Machine Learning
is anything about man-
made intelligence exhibited
by machines.
● Machine Learning (ML) is Deep Learning
an approach to achieve AI.
● Deep Learning (DL) is one technique to implement ML.
Types of ML Algorithms
● Supervised Learning
Machine Learning
0 trained with labeled data; including
regression and
classification problems
Supervised Learning
● Unsupervised Learning
0 trained with unlabeled data;
clustering and association rule Unsupervised Learning
learning problems.

Reinforcement Learning
● Reinforcement Learning
0 no training data; stochastic Markov decision process; robotics and
self-driving cars.
What is Deep Learning?
Deep learning is a class of machine learning algorithms that:
● use a cascade of multiple layers of nonlinear processing units
for feature extraction and transformation. Each successive
layer uses the output from the previous layer as input.
● learn in supervised (e.g., classification) and/or unsupervised
(e.g., pattern analysis) manners.
● learn multiple levels of representations that correspond to
different levels of abstraction; the levels form a hierarchy of
concepts.

(Source: Wikipedia)

Why Deep Learning?


● Limitations of traditional machine learning algorithms ○ not
good at handling high dimensional data.
0 difficult to do feature extraction and object recognition.

● Advantages of deep learning


0 DL is computationally expensive, but it is capable of
handling high dimensional data.
○ feature extraction is done automatically.
Artificial Neural Network
Input Hidden Layers Output
(Image Credit: Wikipedia)
Inputs and Outputs 256 X 256
Matrix

DL model

4-Element
Vector

X Y

1
2 A
3 C M
4 T F
5 G
6

With deep learning, we are searching for surjective


a
Learning
Principle
Dataset

Error:
-
(Image Credit: NVIDIA Deep Learning
Institute)
Learning
Principle

Output/Prediction

Target Output
x x ….. x
Error:
1 2
- n

(Image Credit: NVIDIA Deep Learning


Institute)
Learning
Principle

=5

Error:
-
(Image Credit: NVIDIA Deep Learning
Institute)
Learning
Principle
Output/Prediction

Target Output
x x ….. x
1 2 n

Error:
-
(Image Credit: NVIDIA Deep Learning
Institute)
Learning
Principle
= 15

Error:
-
(Image Credit: NVIDIA Deep Learning
Institute)
Learning
Principle
Output/Prediction

Target Output
x x ….. x
1 2 n

Error:
-
(Image Credit: NVIDIA Deep Learning
Institute)
Learning
Principle
= 2.5

Error:
-
(Image Credit: NVIDIA Deep Learning
Institute)
Supervised Deep Learning with Neural Networks
Training - Minimizing the Loss
The loss function with regard to weights Input Output
and biases can be defined as

W1, b1 X1

Y2

The weight update is computed by moving W2, b2 X2


a step to the opposite direction of the cost
gradient. L
W3, b3 X3

Iterate until L stops decreasing.


Convolution in 2D
(Image Credit: Applied Deep Learning | Arden Dertat)

Convolution Kernel
(Image Credit: Applied Deep Learning | Arden Dertat)
Convolution on Image
Image Credit: Deep Learning Methods for Vision | CVPR 2012 Tutorial
Activation Functions
Image Credit: towardsdatascience.com
Introducing Non-Linearity (ReLU)
Image Credit: Deep Learning Methods for Vision | CVPR 2012 Tutorial

Max Pooling
(Image Credit: Applied Deep Learning | Arden Dertat)
Pooling - Max-Pooling and Sum-Pooling
Image Credit: Deep Learning Methods for Vision | CVPR 2012 Tutorial

Convolutional Neural Networks


A convolutional neural network (CNN, or ConvNet) is a class of deep, feed-forward
artificial neural networks that explicitly assumes that the inputs are images, which allows
us to encode certain properties into the architecture.
LeNet-5 Architecture (Image Credit: https://becominghuman.ai)

You might also like