Lectures

The course ran in two sections, one taught in Hindi and one in English; each lecture lists its date in each section. Lecture slides for each module, with short videos, notebooks and demos where they exist. The primary textbook is Artificial Intelligence: A Modern Approach by Stuart J. Russell and Peter Norvig. Most slides and notebooks for the learning module are hosted on principles-ai-teaching.

SlidesShort videoNotebookInteractive labReading

Search and planning

Lectures 1–7

Lecture 01	Historical perspectives 5 Jan, both sections.	Annotated slides
Lecture 02	k-nearest neighbours: analysis Hindi section 7 Jan · English section 6 Jan.	Annotated slides
Lecture 03	Asymptotic analysis 12 Jan, both sections.	Annotated slides
Lecture 04	Agents and state spaces Hindi section 14 Jan · English section 13 Jan.	Annotated slides
Lecture 05	Breadth-first and depth-first search 19 Jan, both sections.	Annotated slides
Lecture 06	A* search Hindi section 21 Jan · English section 20 Jan.	Annotated slides
Lecture 07	Alpha–beta pruning Hindi section 28 Jan · English section 27 Jan.	Annotated slides

Learning

Lectures 8–15

Lecture 08	Introduction to machine learning Hindi section 4 Feb · English section 3 Feb.	Slides (PDF) What is ML?Types of ML Classification vs regression
Lecture 09	Data foundation ML paradigms, features and labels, train–test split, scikit-learn. 9 Feb, both sections.	Slides Slides (PDF) Train vs test
Lecture 10	Supervised learning: linear regression Hindi section 11 Feb · English section 10 Feb.	Slides Slides (PDF) What is LR?Matrix form Error and objective Normal equation Worked example Outliers Basis expansion
Lecture 11	Supervised learning: linear regression (continued) 16 Feb, both sections.	Slides Slides (PDF)
Lecture 12	Supervised learning: logistic regression Hindi section 18 Feb · English section 17 Feb.	Slides Slides (PDF) Why LR fails Sigmoid LR model Decision boundary Why not MSE?Cross-entropy Gradient and learning Non-linear boundaries
Lecture 13	Neural networks: multilayer perceptrons Perceptrons, logic gates, XOR, MLPs, activations, forward propagation. 9 Mar, both sections.	Slides (PDF) Features to learning Perceptron Logic gates XOR problem Activations MLP Forward propagation Vectorised XOR solved Notebook: Power of neural networks Notebook: Perceptron
Lecture 14	Neural networks: autograd Backpropagation, autograd, the training loop. English section 10 Mar.	Slides (PDF) Why Autodiff?Computation graphs Backpropagation Full backward pass Autograd engine Notebook: Autodiff Notebook: Fully connected network visualiser Autograd playground
Lecture 15	Next-token prediction Embeddings, next-character prediction, an MLP for generation. 16 Mar, both sections.	Slides (PDF) What is NTP?Indian names dataset Training set Character embeddings Embedding lookup Full architecture Training Generating names Colab notebook: Next character GPT demo

Reasoning and decision making

Lectures 16–22

Lecture 16	Probabilistic reasoning Hindi section 18 Mar · English section 17 Mar.	Slides
Lecture 17	Decision trees and expert systems Hindi section 25 Mar · English section 24 Mar.	Slides
Lecture 18	Evaluation metrics Hindi section 1 Apr · English section 30 Mar.	Slides
Lecture 19	Sequential decision making: utilities and MDPs 6 Apr, both sections.	Slides
Lecture 20	Sequential decision making: solving MDPs 7 Apr, both sections.	Slides
Lecture 21	Passive reinforcement learning 8 Apr, both sections.	Slides
Lecture 22	Active reinforcement learning 13 Apr, both sections.	Slides
	Module 3 quiz 25 Apr, both sections.	Question papers

Search and planning

Historical perspectives

k-nearest neighbours: analysis

Asymptotic analysis

Agents and state spaces

Breadth-first and depth-first search

A* search

Alpha–beta pruning

Learning

Introduction to machine learning

Data foundation

Supervised learning: linear regression

Supervised learning: linear regression (continued)

Supervised learning: logistic regression

Neural networks: multilayer perceptrons

Neural networks: autograd

Next-token prediction

Reasoning and decision making

Probabilistic reasoning

Decision trees and expert systems

Evaluation metrics

Sequential decision making: utilities and MDPs

Sequential decision making: solving MDPs

Passive reinforcement learning

Active reinforcement learning

Module 3 quiz