CEP, IIT Delhi Artificial Intelligence and Machine Learning for Industry

• Foundations of Python Programming (TimesPro)

Motivations and Introduction to different ML Paradigm

Linear Algebra for ML

• Vectors and Matrices

• Vector Space and Subspace

• System of Linear Equations

• The Concept of Rank and Independent Vectors

• Inner Product Space

• Norms, Positive Definite Matrix

• Matrix factorisation (EVD, SVD, QR, LR, etc.)

• Projection and Orthogonality

Probability and Statistics for Data Science

• Random Variables

• Distribution and Density Functions

• Conditional Probability, Bayes Theorem

• Joint Distribution

• Concept of Independence, Covariance, and Correlation

• Introductory Statistical Inference (Likelihood, MAP, etc.)

• Concept of Entropy

• Mutual Information, and KL Divergence

Optimisation

• Function and Derivatives

• Gradient Descent

• Stochastic Gradient Descents

• Convex Optimisation

• Formulation and Optimality Conditions

• ADAM Optimiser

Hands-on Demo 1: Linear Algebra using NumPy

• Concepts of Linear Algebra and Probability Basics

• Optimisation with Practical ML Applications

• Simple and Multiple Linear Regression

- Hands-on Demo 2: SLR/MLR

• Least Squares Approach

- Moving Beyond Linearity: Non-linear Regression

- Hands-on Demo 3: NLR

• Model Selection, Regularisation and Bias-Variance Trade-off

- M2 Project: Regression application

Motivation and Introduction to Classification Problems

Logistic Regression

• Logistic Regression

- Hands-on Demo 4: Logistic Regression

Decision Tree

• Introduction to Decision Trees

• Random Forests, Bagging, and Boosting

- Hands-on Demo 5: Random Forests

• Interpretability of Machine Learning Models

Hyperplanes

• Concept of Hyperplane Classifier

SVM

• Support Vector Machines, Kernel SVM

- Hands-on Demo 6: SVM

• Multi-class Classifiers

Clustering

• Clustering Methods

- Hands-on Demo 7: Clustering

M3 Project

• Classification Application

Convolutional Neural Networks

• Fundamentals of Convolution

• Convolutional Neural Network Architecture

- Hands-on Demo 9: CNN

Recurrent Neural Networks/LSTM

• Introduction to Time Series and Sequential Data

• Introduction to Language Modelling and NLP

• Recurrent Neural Network and LSTM/GRU

• Hands-on Demo

Graph Neural Networks

• Introduction to Graph Data

• Graph Neural Network Architecture

• Hands-on Demo

Transformers

• Core mechanics: Self-attention, Positional encodings, Causal mask

• Efficiency & Fine-tuning: Flash/linear Attention, LoRA-FT/ adapters

• Multimodal Extensions: Vision-language Models

Generative AI

• Autoencoder, Variational Autoencoders, Generative Adversarial Networks (GANs)

• Diffusion for images and text modalities

LLM Alignment

• Alignment Pipeline: SFT → reward model → RLHF/DPO/PPO

• Alternative Approaches: Constitutional AI, RLAIF

• Create Persona

• Customer Journey Map

• ROI Calculations

• AI as Persona, Scenario, Task, Task flow, persuasive tools

• UX and Usability testing

Note: Faculty will be conducting Q&A/Doubt-clearing sessions twice a month. Each lecture is accompanied by a hands-on demo session along with a student project. There will be two modes of interaction: a telegram announcement group (read-only) and a discussion forum on the LMS.

1. Linear Regression Lab — Forecast sales using ad expenditure data.

2. Logistic Regression Lab — Sentiment analysis of consumer reviews.

3. Decision Tree, Random Forest, XGBoost — In-depth analysis on benchmark datasets.

4. Support Vector Machines — Image classification (fashion MNIST) and SVM formulations.

5. Neural networks — Layer implementations, gradient descent/backpropagation, comparisons with SVM.

6. Convolutional Neural Networks (CNN) — Computer vision, layer visualisations, GRADCAM.

7. Sequential Model (RNN/LSTM) — Caption/summary generation from images/videos.

8. Variational AutoEncoder — VAE implementation on MNIST.

9. Generative Adversarial Networks — GANs on benchmark datasets.

10. Graph Neural Network — GCN, GraphSage variants; recommender and biomedical use-cases.

11. Natural Language Processing — Text summarisation.

12. Course Project — Build a recommender system using any discussed techniques (GNN, CNN, LSTM, classical ML, etc.).

Note: Career support facility is offered by TimesPro. IIT Delhi is not responsible for the same.

Faculty will be conducting Q&A/Doubt-clearing sessions twice a month.

• Each lecture is accompanied by a hands-on demo session along with a student project (part of 110 hours).

- Two modes of interaction: telegram announcement group (read-only) and discussion forum on the LMS.