Course Content
Basics of pattern recognition, Neural networks. Introduction to deep learning, convolutional networks, Applications in audio, image and text. All coding done in Python.Contact Details
Instructor  Sriram Ganapathy 
Office  Electrical Engineering C 334 (2nd Floor) 
deeplearning doT cce2020 aT gmail doT com  
Teaching Assistants  Prachi Singh (Electrical Engineering C 328 (2nd Floor)) 
Textbooks
 “Pattern Recognition and Machine Learning”, C.M. Bishop, 2nd Edition, Springer, 2007.
 “Neural Networks”, C.M. Bishop, 2nd Edition, Springer, 1995.
 “Deep Learning”, I. Goodfellow, Y, Bengio, A. Courville, MIT Press, 2016. html
Prerequisites
 Random Process/Probablity and Statistics  Recommended Book "Probability and Statistics" by Stark and Woods. Video Lectures
 Linear Algebra/Matrix Theory  Recommended book "Linear Algebra", by G. Strang  Author's webpage for Videos and Text
 Basic Programming with Python  numpy based array and matrix operations.
 Calculus
Announcements
 Final class on May 14,2020
 Final Exam on June 7, 2020 from 6pm. Open book and notes. Online exam, question paper sent through email and answers returned over email before deadline.
 Google group for discussions and announcements: dl_cce2020
Slides
16012020  Introduction to Deep Learning Course. Examples. Roadmap of the course. 
slides 
code 
23012020  Decision Theory for Machine Learning. Maximum Posterior Probability Rule. Minimum mean square estimation for Regression. 
slides  
622020  Matrix Calculus. Differentiating vectors and matrices. Principal Component Analysis. Preprocessing data  standardizing and whitening. 
slides  
1322020  Linear Regression. Regularization. Least squares model for classification. Logistic regression Lecture1. 
slides  
2022020  Linear Regression. Regularization. Least squares model for classification. Logistic regression Lecture2. 
slides  
Second assignment due on March 10.

HW2.pdf  Preprocessing code  
2722020  Linear Regression. Regularization. Least squares model for classification. Logistic regression Lecture3. 
slides  
532020  Midterm Exam 

1232020  Neural networks with one or more hidden layers. Error function. Model update using gradient descent. Backpropogation algorithm. Stochastic gradient descent algorithm. 
slides  
Third assignment due on April 17.

HW3.pdf  Preprocessing code  
02042020  Discussion on Depth Versus Width. Practical considerations in Deep Learning. Avoiding Overfitting Regularization, Dropout. Convolutional Neural Networks. 
slides
Video 

09042020  Dropout in detail. Training and Testing with Dropouts. Convolutional neural networks. Convolution, maxpooling operations. 
slides
Video 

16042020  CNNs in detail. DNN versus CNN in terms of number of parameters. Backpropogation in CNNs. Convolution and Maxpooling backpropagation. 
slides
Video 

23042020  tSNE (tdistributed stochastic neighborhood embedding) for data visualization. Understanding deep networks using tSNE. Using image classification examples. Identifying representation learning using reconstruction. Deep networks in speech processing. 
slides
Video 

30042020  Recurrent Neural Networks. Forward and Backward propagation. Various Architectures for sequence to sequence and sequence to vector mapping. 
slides
Video 

07052020  Recap of recurrent networks. Architectures for vector to sequence mapping and encoder decoder sequences. Introduction to LSTMRNNs. Attention mechanism in encoder decoder models 
slides
Video 

14052020 
Fourth assignment due on May 31. 
HW4.pdf  
14052020  Recap of attention mechanism in encoder decoder models. Unsupervised models for deep learning. Autoencoders and generative adversarial networks. Image generation using GANs. 
slides
Video 