Syllabus for CS/EECE 547
Under Construction
- Aug 20
intro.
Three paths to Neural Networks:
- biology / neuroscience
- psychology / cognitive science
- engineering / statistics
Neuroscience:
- Real neurons are very slow but the brain is fast.
- Other interesting properties of the nervous system.
- Neurons come in many shapes but share many common features.
- Aug 22
batch and online linear regression. input space, weight space.
- Aug 27
linear discrimination, discrimination surface, perceptron
learning rule (assignment one)
- Aug 29
- generalization: cross validation
- backpropagation
- Q: when will linear decision surface be optimal?
A: requires probabilistic framework and Bayes rule.
- gaussian mixture models
- Asymptotic analysis of deterministic simple gradient descent
- convolutional networks
- weight sharing
-
- competitive learning
-
- Boltzmann machines
- Helmholtz machines
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Barak Pearlmutter
<bap@cs.unm.edu>