IE 643 - Deep Learning Theory & Practice

Course content
  • The Perceptron, Feed-forward networks and Multi-layer perceptron, Memory based networks like Boltzmann Machines, Hopfield Networks.
  • State based networks like Recurrent Neural Networks, Long Short Term Memory Networks. Convolutional Neural Networks, Bidirectional networks, Concept based networks used for transfer learning, Structural Networks for structured prediction, Attention based networks, Auto encoders for dimension reduction and embedding, Generative Adversarial Networks, Deep Gaussian Processes, Deep Bayesian nets, Deep Search Models, Deep Reinforcement Learning, Deep Neural Recommenders. Non-convex Optimization tools for Deep Networks.
  • Theoretical tools to describe Convolutional Neural Networks and Recurrent Neural Networks. Learning theory for Deep Neural Networks.
  • Several Applications covering operations research, computer vision, natural language processing, multi-media analytics, proof checking
  • Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. MIT Press. 2017.302225
  • Deep Learning with Python by Fran303247ois Chollet. Manning Publication. 2017.10.3.
  • Pattern Recognition and Machine Learning by Christopher Bishop. Springer, 2010.302225
  • The Elements of Statistical Learning: Data Mining, Inference, and Prediction (Second Edition), by Trevor Hastie,Robert Tibshirani, Jerome Friedman. Springer, 2017.
  • Free e-book at by Michael Nielsen.302225
  • Code websites:,,
Pre-requisite : N/A
Total credits : 6
Type :
Duration : Autumn 2022
Name(s) of other Academic units to whom the course may be relevant : N/A