Comprehensive Course on AI Fundamentals and Advanced Techniques
Interactive lectures, hands-on programming, and real-world applicationsSE444 is a comprehensive artificial intelligence course covering fundamental concepts, algorithms, and practical applications. Each lecture includes interactive demonstrations, step-by-step explanations, and hands-on programming exercises to reinforce learning.
Comprehensive coverage of search algorithms including BFS, DFS, UCS, Greedy Search, and A*. Features interactive visualizations and step-by-step algorithm comparisons using Saudi city examples.
Overview of artificial intelligence, its history, applications, and current state. Introduction to different AI paradigms and problem-solving approaches.
Understanding intelligent agents, agent architectures, environment types, and agent performance measures. Rational agents and agent design principles.
Hill climbing, simulated annealing, genetic algorithms, and optimization techniques. Interactive demonstrations with N-Queens, TSP, and visual search landscapes.
Complete minimax algorithm walkthrough with interactive tic-tac-toe demos. Features step-by-step explanations, alpha-beta pruning, depth-limited search, and multiple evaluation perspectives.
Interactive CSP formulation, backtracking search with visualization, constraint propagation demos, and smart heuristics. Features Saudi map coloring, N-Queens, and Sudoku solver examples.
Comprehensive coverage of knowledge-based agents, logical reasoning, propositional and first-order logic, inference techniques, and the classic Wumpus World case study. Features step-by-step reasoning demos.
Supervised, unsupervised, and reinforcement learning. Decision trees, neural networks, and basic ML algorithms with practical examples.
Complete coverage of classical planning with STRIPS and PDDL representations. Interactive visualizations of forward search, backward search, and SAT-based planning with Saudi Air Cargo and Spare Tire examples.
Paradigm shift from formal logic to probabilistic reasoning. Explores why AI needs uncertainty modeling, covering probability theory fundamentals, Bayes' rule, and the philosophical contrast between absolute and partial knowledge.
Comprehensive coverage of Bayesian Networks as compact representations of joint distributions. Features conditional independence, d-separation, exact inference (variable elimination, belief propagation), and approximate methods (MCMC, Gibbs sampling) with real-world applications.
Rational decision-making under uncertainty using utility theory. Covers preference modeling, expected utility maximization, value of information, and decision networks with real-world applications in medical diagnosis and resource allocation.
Multi-player strategic games and Nash equilibrium. Covers dominant strategies, best response analysis, mixed strategies, and applications in AI, economics, and multi-agent systems.
Apply everything you've learned in an integrated semester project. Build an intelligent agent that navigates a grid world using search algorithms, logical reasoning, and probabilistic inference.
Technologies: Python, Pygame, NumPy, Matplotlib
Duration: 3 weeks (intensive implementation)
Difficulty: Progressive (starts easy, builds up)
⚠️ Tight deadline - Start immediately!