A study of the basic structure of neural networks and how machines may learn. This will include analyses of decision trees, Bayesian learning, genetic algorithms, PAC, analytical and reinforcement learning. Neural networks to be studied include Hopfield, backpropagation, Kohonen, ART, and Neuro-Fuzzy. Students will explore current applications and design several learning systems. No prior background in artificial intelligence is assumed. PREREQUISITE(S): MAT 220 or MAT 262 or MAT 151.