Schedule
Class Schedule
Updated October 26, 2026. Lectures 1–7 list the material covered through October 21. Topics for Lectures 8–13 (October 28–December 2) are tentative and may be adjusted as the course progresses.
Slides and additional material can be found here.
Class scribbles from 2021 can be found here.
| Lec | Date | Topic | Readings | Problem Sheet | Scribbles and Slides | Recordings | Optional Readings |
|---|---|---|---|---|---|---|---|
| 1 | 26 Aug 2026 | Introduction and Logistical Details, Supervised Learning, Generalization, Linear Regression, Least Squares, MSE and RMSE | LN Chapter-01, Prince Chapter-01 | Problem Sheet 0 Pre-requisites | Slides, Slides (Part 2) | Not recorded this year. Last year’s recordings are available here. | Computing Machinery and Intelligence by Alan Turing, Probability Review, Linear Algebra Review |
| 2 | 02 Sep 2026 | Basis Functions, Polynomial Regression, Overfitting, Train/Validation/Test Splits, Ridge, Lasso, and Gradient Methods | LN Chapter-01, LN Chapter-02, Bishop section 1.1, 3.1, HTF section 2.3 | Problem Sheet 1 (Linear Regression and Gradient Descent) | Slides | idem | The Saga of Highleyman’s Data by Moritz Hardt and Ben Recht. |
| 3 | 09 Sep 2026 | Finish Gradient Methods, K-Nearest Neighbors, and Introduction to Statistical Learning | LN Chapter-02, HTF section 3.4.1, 3.4.2 | Problem Sheet 2, Notebook | Slides | idem | Implicit Gradient Regularization, Double Descent |
| 4 | 16 Sep 2026 | Classification through ERM, Convex Surrogate Losses, and Logistic Regression | LN Chapter-03, Chapter-04, HTF section 2.4, 2.5, Bishop section 3.2 | Problem Sheet 3, Notebook | Slides | idem | |
| 5 | 23 Sep 2026 | Maximum-Margin Classification: Hinge Loss, Support Vectors, and Kernels | LN Chapter-08, Bishop section 7.1 | Slides | idem | ||
| 24 Sep 2026 [Lab Time] | First Quiz [5 pm to 6:30 pm] | Math Sheet | |||||
| 30 Sep 2026 | Federal Holiday - No Class | ||||||
| 6 | 07 Oct 2026 | Perceptron, XOR and Hidden Features, Multilayer Neural Networks, Backpropagation, and Function Approximation | LN Chapter-08, Chapter-11, Bishop section 4.1.7, Rojas Chapter 7 | Slides | idem | ||
| 14 Oct 2026 | Fall Break - No Class | ||||||
| 7 | 21 Oct 2026 | Neural Network Training Difficulties, Initialization, Batch Normalization, Input and Target Preprocessing, and PCA | LN Chapter-11, Chapter-12, Chapter-14 | idem | |||
| 8 | 28 Oct 2026 | Tentative: Cost-Sensitive Classification, Class Imbalance, ROC/AUROC, One-Class SVM, Decision Trees, and Introduction to Random Forests | LN Chapter-05, Chapter-06, Chapter-07, Chapter-09, Bishop sections 4.1.1, 4.1.2, TSKK section 3.3, Mitchell Chapter 03 | idem | |||
| 9 | 04 Nov 2026 | Tentative: Random Forests, Bagging, Boosting, Stacking, Bias–Variance Decomposition, Cross-Validation, and Hyperparameter Selection | LN Chapter-10, Bishop Chapter 14, Stacking paper | idem | |||
| 05 Nov 2026 [Lab Time] | Second Quiz [5 pm to 6:30 pm] | ||||||
| 10 | 11 Nov 2026 | Tentative: Deep Neural Networks, Training Stability, Convolutional Neural Networks, and Architectural Inductive Bias | LN Chapter-11, Chapter-12, Rojas Chapter 7 | idem | |||
| 11 | 18 Nov 2026 | Tentative: Probabilistic Modelling, Generative Classification, Maximum Likelihood, and MAP Estimation | LN Chapter-03, Chapter-05, Chapter-06, Chapter-15, Bishop section 4.2, Bishop Chapter 3.3, Parameter Estimation | idem | |||
| 12 | 25 Nov 2026 | Tentative: Bayesian Learning, Calibration and Predictive Uncertainty, Bayesian Regression, and Gaussian Processes | LN Chapter-15, Bishop Chapter 3.3, Parameter Estimation | idem | |||
| 26 Nov 2026 [Lab Time] | Coding Exam [5 pm to 7 pm] | ||||||
| 13 | 02 Dec 2026 | Tentative: Sequence Models, Self-Supervised Learning, Grokking, Course Synthesis, and Questions | LN Chapter-17 | idem | |||
| Early to mid December 2026 [Date and Time TBD] | Final Exam |
Tutorials
| Lec | Date | Time | Topic | Lecture Videos| Lecture Materials| |:——-:|:——–:|———–|———–|———————-|———————-|