What this course is all about
Artificial Intelligence (AI) addresses one of the ultimate puzzles humans are trying to solve: How is it possible for a brain, whether biological or electronic, to perceive, understand, predict and manipulate a world far larger and more complicated than itself? And how do people create a machine (or computer) with those properties? To that end, AI researchers try to understand how seeing, learning, remembering and reasoning can, or should, be done. This course introduces students to the many AI concepts and techniques including perception, probabilistic reasoning over time, logical reasoning, planning with and without interactions with the environment, reinforcement learning and natural language understanding.Topics Covered
Statistical Learning Theory
The learning problem, entropy, optimization fundamentals, and classification basics.
Deep Neural Networks
Fundamentals of deep learning, network architectures, forward propagation, and backpropagation.
Large Language Models
RNNs, LSTMs, transformers, and self-attention mechanisms for language understanding.
Logical Reasoning
Propositional logic, automated reasoning, logical inference, and intelligent agents.
Task Planning
PDDL-based planning, logistics, and manufacturing applications.
Reinforcement Learning
Model-based and model-free algorithms, policy gradient methods, and value-based control.