Introduction to the contemporary concepts and techniques of artificial intelligence, including any or all of: machine perception and inference, machine learning, optimization problems, computational methods and models of search, game playing and theorem proving. Emphasis may be on any formal method of perceiving, learning, reasoning, and problem solving which proves to be effective. This includes both symbolic and neural network approaches to artificial intelligence. Issues discussed include symbolic versus nonsymbolic methods, local versus global methods, hierarchical organization and control, and brain modeling versus engineering approaches. Lisp or Prolog may be introduced. Involves one major project or regular programming assignments. (Formerly CMPS 140.)
Prerequisites:
Quality:
Difficulty:
Remarks:
- Language(s) used: Python
- STUDY FOR EXAMS
- Assignments are usually autograded (Start early)
- Hardest concepts are heuristic admissibility/consistency, Q-learning, and Bayesian networks