Teaching & Courses

This comprehensive course covers the entire spectrum of Generative AI, from its historical foundations to cutting-edge applications. Topics include the history of Generative AI, how text generation models work, RAG (Retrieval-Augmented Generation) systems, all aspects of prompting techniques, LLM fine-tuning methodologies, and agentic AI for building intelligent autonomous agents.

A comprehensive journey through Deep Learning, covering fundamental concepts to advanced architectures. The course discusses deep learning from scratch including core concepts and mathematical foundations, Artificial Neural Networks (ANN) as building blocks, feedforward networks architecture and implementation, backpropagation for training neural networks effectively, Recurrent Neural Networks (RNN) for sequential data processing, and LSTM (Long Short-Term Memory) architecture and applications.

Deep dive into Convolutional Neural Networks (CNN) for computer vision applications. This course covers introduction to CNN and why CNNs are essential for image processing, feature extraction and how CNNs learn visual patterns, image classification and building classification models, CNN components including convolutional layers, pooling, and activation functions, popular architectures like LeNet, AlexNet, VGG, and ResNet, and transfer learning for leveraging pre-trained models.

Comprehensive introduction to Reinforcement Learning covering theoretical concepts and practical implementations. Topics include understanding the RL paradigm, building blocks of RL (agents, environments, rewards, policies), Markov Decision Processes as the mathematical framework for RL, basic RL algorithms including Q-Learning, SARSA, and Policy Gradient, value functions covering state-value and action-value functions, and exploration vs exploitation balancing strategies.