Artificial Intelligence

Catalog description

This course covers advanced topics in artificial intelligence. Topics include search and optimization, simulated annealing, evolutionary algorithms, gradient optimization, constraint optimization, A* search, alpha-beta search, Monte Carlo tree search, prob abilistic reasoning, Bayesian networks, hidden Markov models, Kalman filters, decision-making under uncertainty, influence diagrams, Markov decision processes, bandit problems, supervised learning, classification, deep learning, reinforcement learning, kno wledge representation, propositional and first -order logic, ontological engineering, AI ethics and safety, privacy, bias and fairness in machine learning, and explainable AI. MAI 510 Deep Learning (3 credit hours) This course delves into advanced topics in deep learning, encompassing optimization, computer vision, computer graphics, unsupervised feature learning, deep language models, and deep learning for games. The class structure in delve into the foundational el ements and insights behind designing, training, fine - tuning, and monitoring deep networks. The course explores both the theoretical aspects of deep learning and practical implementation sessions using PyTorch. Through homework assignments, students will create a vision system for a racing simulator, SuperTuxKart, starting from scratch. delves into various application areas of deep networks, including computer vision, sequence modeling in natural language processing, deep reinforcement learning, generative modeling, and adversarial learning.