Create README.md

Author: llSourcell

README.md

@@ -0,0 +1,49 @@
+# Learn_Deep_Learning_in_6_Weeks
+This is the Curriculum for "Learn Deep Learning in 6 Weeks" by Siraj Raval on Youtube 
+
+
+## Overview
+
+This is the curriculum for [this](https://youtu.be/_qjNH1rDLm0) video on Youtube by Siraj Raval
+
+## Week 1 - Feedforward Neural Networks and Backpropagation
+
+- Read Part I of the Deep Learning Book found [here](http://www.deeplearningbook.org/) 
+- Use this cheat sheet to help understand any math notation, found [here](https://www.flickr.com/photos/95869671@N08/40544016221)
+- Watch [Build a Neural Net in 4 Minutes](https://www.youtube.com/watch?v=h3l4qz76JhQ
+- Read [Neural Net in 11 lines](https://iamtrask.github.io/2015/07/12/basic-python-network/) 
+- Type out the neural network code yourself in a text editor, compile, and run it locally (using no ML libraries)
+- Watch [Backpropagation in 5 minutes](https://www.youtube.com/watch?v=q555kfIFUCM)
+
+## Week 2 - Convolutional Networks
+
+- Watch the Convolutional Networks Specialization on Coursera, found [here](https://www.coursera.org/learn/convolutional-neural-networks). 
+- Read all 3 lecture notes under Module 2 for Karpathy CNN course found [here](http://cs231n.github.io/)
+- Watch my video on CNNs [here](https://www.youtube.com/watch?v=FTr3n7uBIuE&t=1782s) and [here](https://www.youtube.com/watch?v=cAICT4Al5Ow&t=4s)
+- Write out a simple CNN yourself (using no ML libraries)
+
+## Week 3 - Recurrent Networks
+
+- Watch the Sequence Models Specialization on Coursera, found [here](https://www.coursera.org/learn/nlp-sequence-models)
+- Watch my videos on recurrent networks, [here](https://www.youtube.com/watch?v=BwmddtPFWtA&t=4s), [here](https://www.youtube.com/watch?v=cdLUzrjnlr4), and [here](https://www.youtube.com/watch?v=9zhrxE5PQgY&t=25s)
+- Read Trask's blogpost on LSTM RNNs found [here](https://iamtrask.github.io/2015/11/15/anyone-can-code-lstm/)
+- Write out a simple RNN yourself (using no ML libraries)
+
+## Week 4 - Tooling
+
+- Watch CS20 (Tensorflow for DL research). Slides are [here](http://web.stanford.edu/class/cs20si/syllabus.html). Playlist is [here](https://www.youtube.com/watch?v=g-EvyKpZjmQ&list=PLDuNt91tg0urwwTQNKyUbncSDvMEl74ww)
+- Watch my intro to tensorflow playlist [here](https://www.youtube.com/watch?v=2FmcHiLCwTU&list=PL2-dafEMk2A7EEME489DsI468AB0wQsMV)
+- Read Keras Example code to quickly understand its structure [here](https://keras.io/getting-started/sequential-model-guide/)
+- Learn which GPU provider is best for you [here](https://medium.com/@rupak.thakur/aws-vs-paperspace-vs-floydhub-choosing-your-cloud-gpu-partner-350150606b39)
+- Write out a simple image classifier using Tensorflow
+
+## Week 5 - Generative Adversarial Network
+- Watch the first 7 videos you see [here](https://www.youtube.com/results?search_query=generative+adversarial+network)
+- Build a GAN using no ML libraries
+- Build a GAN using tensorflow
+- Read this to understand the math of GANs, but don't worry if you dont understand it all. This is the bleeding edge [here](https://lilianweng.github.io/lil-log/2017/08/20/from-GAN-to-WGAN.html)
+
+## Week 6 - Deep Reinforcement Learning
+- Watch CS 294 [here](http://rail.eecs.berkeley.edu/deeprlcourse/) 
+- Build a Deep Q Network using Tensorflow
+