Syllabus for CS/EECE 547

Under Construction
  1. Aug 20
    intro.
    Three paths to Neural Networks: Neuroscience:
  2. Aug 22
    batch and online linear regression. input space, weight space.
  3. Aug 27
    linear discrimination, discrimination surface, perceptron learning rule (assignment one)
  4. Aug 29
  5. generalization: cross validation
  6. backpropagation
  7. Q: when will linear decision surface be optimal? A: requires probabilistic framework and Bayes rule.
  8. gaussian mixture models
  9. Asymptotic analysis of deterministic simple gradient descent
  10. convolutional networks
  11. weight sharing
  12. competitive learning
  13. Boltzmann machines
  14. Helmholtz machines

Barak Pearlmutter <bap@cs.unm.edu>