Topics ranging from fundamental learning rules, functional, cascade correlational, recurrent and gradient descent networks, to neocognitron, softmax, deep convolutional networks, autoencoders, and pre-trained deep learning (restricted boltzmann machines). Students will be required to work in teams on class paper. The course will assume undergraduate-level background in programming, algorithms, linear algebra, calculus, statistics, and probability. Prerequisites: Graduate student standing in computer science or acceptance into accelerated B.S. to M.S. program in computer science.
|•||3:30-4:45 PM||•||3:30-4:45 PM||•||•|
Dr. Gregory Triplett • Ph: (804) 828-5387 • firstname.lastname@example.org