| Topic | Recommended Reading | |
| 1 | Introduction to Machine Learning, Classification using Bayes rule | Duda and Hart: Chapter 2 |
| 2 | Introduction to Bayes Decision Theory | Duda and Hart: Chapter 2 |
| 3 | Bayes Decision Theory (Contd...) | Duda and Hart: Chapter 2 |
| 4 | Learning as Optimization, Linear Regression | Bishop: Chapter 3 |
| 5 | Probabilistic view of Linear Regression: ML and MAP estimates | NA |
| 6 | Logistic Regression: Optimization and Probabilistic approaches | NA |
| 8 | Parameter estimation for Logistic Regression: Gradient Descent, Stochastic Gradient methods | NA |
| 7 | Hyperplane based classifiers, Perceptron, and Perceptron Convergence Theorem | NA |
| 8 | Introduction to Support Vector Machines | NA |
| 9 | Support Vector Machines | NA |
| 10 | Kernel Methods and Kernel SVM | NA |
| 11 | Feedforward Neural Network and Backpropagation Algorithm | NA |
| 12 | Undirected Graphical Models, Markov Random Fields | An Introduction to Restricted Boltzmann Machines |
| 13 | Introduction to MCMC and Gibbs Sampling | Chapter 11, Bishop Sections: 11.1.5, 11.2.1 Markov Chain Monte Carlo (MCMC) |
| 14 | Restricted Boltzmann Machine | An Introduction to Restricted Boltzmann Machines A Practical Guide to Training Restricted Boltzmann Machines |
| 15 | Boltzmann Machine and Variational methods | https://onlinelibrary.wiley.com/doi/abs/10.1207/s15516709cog0901_7 Boltzmann Machines |
| 16 | Variational methods (contd...) | Variational methods (See Section 6.3.1) |
| 17 | EM algorithm, Mixture models and K-means | Bishop: Chapter 9 |
| 18 | Bayesian Networks, Introduction to HMMs | Tutorial on HMM |
| 19 | HMMs (contd...) - Forward Backward algorithm | Tutorial on HMM |
| 20 | Introduction to Undirected Graphical Models and Markov Random Fields | Chapter 8, Bishop |
| 21 | Variational Bayes and Variational autoencoders. | Tutorial on Variational Autoencoders |
| 22 | Convolutional and Recurrent Neural Networks | Tutorial on CNN and RNN Understanding CNN for NLP Understanding LSTM Networks |