Assignments
Lecture notes are available here.
Self-assessment questions for each lecture are available here.
Scribbles for each lecture are available here.
| Lec | Date | Topics | Lecture Material | Video Lecture | Reference | Readings |
|---|---|---|---|---|---|---|
| 1 | 30 Aug | Intro to ML, Linear Regression | Chapter-1 | video1 video2 video3 | Bishop section 1.1 , HTF section 2.3 |
Computing Machinery and Intelligence by Alan Turing, Probability Review, Linear Algebra Review |
| 2 | 13 Sep | Linear Regression, Overfitting, ML Pipeline, Classification, k-NN, More on Regression,Gradient Descent | Chapter-1, Chapter-2 | video1 video2 video3 | Bishop section 1.1, 3.1, 3.1.4, HTF section 2.3, 2.4, 2.5 ,3.4.1, 3.4.2 |
|
| 3 | 20 Sep | Gradient Descent, Regularization, Decision theory, Empirical Risk Minimization | Chapter-3 Chapter-4 | video1 video2 video3 | Bishop section 3.1, 3.1.4 HTF section 3.4.1, 3.4.2, 2.4, 2.5 |
|
| 4 | 27 Sep | Bias-Variance Tradeoff, linear classification | Chapter-4 Chapter-5 | video1 video2 video3 | Bishop: Chapter 3 section 3.2 HTF: Chapter 2:section 2.9 and Chapter 10 |
Linear Algebra review (7.1) in this pdf. Lagrange Multiplier (Appendix E in Bishop) |
| 5 | 04 Oct | GLM, GDA, Naive Bayes | Chapter-6 | video1 video2 video3 | HTF:Chapter 4 and Chapter 6.6 | Intro to convex optimization (page 91 to 102 in this book) |
| 11 Oct | —-Break—- | |||||
| 6 | 18 Oct | Logistic Regression, Newton-Raphson method, Evaluation Metrics, Perceptron | Chapter-7, Chapter-6, Chapter-8 | video1 video2 video3 | Bishop: Chapter 5;section 1 and section2 | Generative and discriminative classifiers by Tom Mitchell. |
| 7 | 25 Oct | Max-margin Classifiers, SVMs | Chapter-8 | video1 video2 video3 | Bishop: Chapter 7 section 1 | The Saga of Highleyman’s Data by Moritz Hardt and Ben Recht. |
| 8 | 01 Nov | Decision trees, Ensembles: Bagging, Random Forests, Stacking | Chapter-9, Chapter-10 | video1 video2 video3 | TSKK section 3.3 Mitchell Chapter 3 Bishop Chapter 14 stacking_paper |
A Few Useful Things to Know about Machine Learning by Pedro Domingos |
| 9 | 08 Nov | Boosting, Neural Nets, Backpropagation | Chapter-11 | video1 video2 video3 | Bishop Chapter 14 Rojas Chapter 7 |
|
| 10 | 15 Nov | Backpropagation, Deep Neural Networks, Convolutional Networks | Chapter-11 Chapter-13 | video1 video2 video3 | Rojas Chapter 7 ConvNets |
|
| 11 | 22 Nov | Optimization, Dimensionality Reduction, PCA, LDA | Chapter-12 Chapter-13 Chapte-14 | video1 video2 video3 | Optimization-1 Optimization-2 | |
| 12 | 29 Nov | Bayesian learning, MLE, MAP, Bayesian Linear Regression | Chapter-15 | video1 video2 video3 | Bishop Chapter 3.3, Parameter Estimation |
|
| 13 | 07 Dec | Kernel Methods, Gaussian Process, Frontiers, What Next? | Chapter-16 Chapter-17 | video1 video2 video3 | Bishop: Chapter 6 |
Tutorials
| Lec | Date | Time | Topic | Lecture Materials | Video Lecture |
|---|---|---|---|---|---|
| 1 | 01 Sep | 4 pm to 5 pm | Probability | Probability Material | video |
| 2 | 03 Sep | 9 am to 10 am | Linear Algebra | Linear Algebra Material | video |
| 3 | 08 sep | 4 pm to 5:30 pm | Python, NumPy, Matplotlib | Python, NumPy, Matplotlib Material | video |
| 4 | 22 Oct | 9 am to 10:30 am | scikit-learn | scikit-learn | video |
| 5 | 27 Oct | 4 pm to 5:30 pm | Basic Pytorch | Pytorch notebook , slides | video |
| 6 | 5 Nov | 9 am to 10:30 am | Advanced PyTorch | Pytorch notebook , slides | video |
| 7 | 17 Nov | 4 pm to 5:00 pm | How to write good and reproducible ML code? | - | video |
Note: There might be changes in the topics/plan in the future.