This course offers a structured path to mastering Artificial Intelligence, starting from the basics and gradually moving to advanced concepts. Learn foundational AI principles, problem-solving techniques, and search algorithms including BFS, DFS, Bidirectional Search, Best First Search, A*, AO*, and Hill Climbing. Explore heuristic search strategies and practical examples like the 8-puzzle problem.
Dive into game playing AI, learning Minimax, Alpha-Beta Pruning, and strategies for intelligent decision-making. Understand knowledge representation and reasoning, covering propositional logic, predicate logic, semantic networks, frames, and fuzzy logic operations.
Learn about intelligent agents, their types, and applications, including reflex, model-based, goal-based, and utility-based agents. Gain proficiency in machine learning and neural networks, with practical examples in supervised, unsupervised, reinforcement learning, and genetic algorithms. Explore NLP applications and constraint satisfaction problems for real-world AI challenges.
Advanced topics include probabilistic reasoning, Bayesian networks, sampling methods, and hidden Markov models. Finally, get an introduction to LLMs and token/parameter concepts in modern models like LLama3 and GPT, preparing you for cutting-edge AI research and applications.
