Offered: Fall 2025 (current)
Fundamentals of AI, Genetic Algorithm, Knowledge Representation and Semantic Net, Graphical Models and D-separation, Probability theory and Bayes Net, Markov Decision Process, Expectation Maximization, Hidden Markov Model, Decision theory, Matching Game based Decision theory, Multi-Attribute Decision Making (MADM)-TOPSIS and Fuzzy-TOPSIS, Recommender Engine: Collaborative Filtering, Generative AI: Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and diffusion models, Explainable AI: LIME, SHAP and Reinforcement Learning: Q-learning, Monte Carlo, SARSA.
The core objective of this course are to:
present the advanced concepts, methodologies, and applications of artificial intelligence. Specifically to learn about state-of-the-art AI principles such as problem solving, inference, perception, knowledge representation, and learning
Investigate the use of AI approaches in intelligent agents, decision theory, expert systems, artificial neural networks, and other machine learning algorithms
To gain experience with generative AI and explainable AI methods and implementation tools. Investigate the existing scope, potential, constraints, and consequences of designing intelligent systems
1. To Be Added
| # | Description | Weight | Edit |
|---|
