The Course is divided into 2 main parts:

Part I : Basics of Deep Learning

1. Introduction to Deep Learning
2. Image Classification
3. Loss functions, Regularization and Optimization
4. Neural Networks and Backpropagation
5. Convolutional Neural Networks and its variants
6. Training Neural Networks
7. Explainability via Visualization of CNN features

Part II : Applications in Computer Vision (includes Invited talks)

1. Segmentation, Object Detection and Localization
2. Sequence Modelling (RNNs/LSTMs/Transformers)
3. Generative Models (GANs, VAE, Diffusion models)
4. 3D Vision (Radiance fields, Structure from Motion)
5. Other advanced topics (Self-supervised learning, Adversarial robustness, Video modelling, Machine Unlearning)