Teaching
Autumn 2025, Autumn 2024
AI61201: Visual Computing with AI/ML
Course Instructors: Somdyuti Paul
Syllabus
- Image formation and representation
- The human visual System and modeling visual perception
- Image transformations in the spatial domain
- Image analysis and filtering in the frequency domain
- Multi-resolution representations for images
- Feature design for image analysis and recognition
- Deep neural networks for vision tasks
- Generative models for visual data
- Representation and analysis of videos
- Perceptual quality and compression models for visual data
Spring 2025
AI61002: Deep Learning Foundations and Applications
Syllabus:
- Introduction and historical trends in deep learning
- Perceptron and deep feedforward neural networks
- Backpropagation and optimization using gradient descent based methods
- Regularization techniques for deep networks
- Introduction to convolutional neural networks, standard CNN architectures and their use for classification and regression
- Types of convolution operations and backpropagation through convolutional layers
- Visualization of CNN filters and gradients, and adversarial attacks
- Sequence modeling using recurrent neural networks, types of recurrent units and their roles in resolving long-term dependency issues
- Introduction to attention mechanisms, transformers, and language modeling using BERT and GPT
- Autoencoders and their applications
- Adversarial learning and generative adversarial networks
Spring 2024 (Co-taught part of the course)
AI42001: Machine Learning Foundations and Applications
Syllabus
- Introduction to machine learning, basics of supervised, unsupervised and reinforcement learning
- k nearest neighbours
- Linear models for classification and regression
- Bayesian learning and naive Bayes model
- Bias-variance tradeoff
- Decision Trees
- MLE and MAP estimation
- Support vector machines
- Feedforward neural networks
- Convolutional and Recurrent Neural networks
- Ensemble methods
- Clustering
- Dimensionality reduction using PCA and LDA
- Hidden Markov Models
- Overview of large language models