Course Detail
CSE317
Artificial Intelligence
3 Credit Hour Course
Intended For Level 3 Term 1 Students
Prerequisite:
Introduction to AI, intelligent agents; Solving problems by searching: informed search strategies, greedy best-first search, A* search, inadmissible heuristics and weighted A*, heuristic functions; Local search and optimization problems: hill-climbing search, simulated annealing, local beam search, evolutionary algorithms; Adversarial search and games: alpha-beta tree search, Monte Carlo tree search; Constraint satisfaction problems (CSP): backtracking and local search for CSPs; Knowledge, reasoning, and planning: logical agents, inference in first-order logic, knowledge representation, automated planning; Learning from examples: forms of learning, supervised learning, learning decision trees, model selection and optimization, theory of learning; Parametric models: linear regression and classification; Nonparametric models: nearest-neighbor models, support vector machines (SVM); Ensemble learning: bagging, random forests, stacking, boosting, gradient boosting, online learning; Markov decision process (MDP), partially observable MDP, learning from rewards, passive and active reinforcement learning, Q-learning, policy search; Robotics: robotic perception, planning and control, reinforcement learning in robotics; Ethics and future of AI.