Texts:

1. Required: Neural Networks for Pattern Recognition, Chris Bishop, Publisher: Oxford University Press.
2. Recommended: Neural Networks: A Comprehensive Foundation, Simon Haykin, Publisher: Macmillan.
3. Other Material: Class notes and papers from the following: Neural Computation, IEEE TNN, Neural Networks, Biological Cybernetics, Network.

Office hours: MWF 4-5pm or by appointment.

Grading:

1. Homeworks: 25%.
2. Two Midterms: 25% each.
3. Project: 25%

1. Prerequisites: A familiarity with basic concepts in calculus, linear algebra, and probability theory. A partial list of basic requirements follows. Calculus: Differentiation, chain rule, integration. Linear algebra: Matrix multiplication, inverse, pseudo-inverse. Probability theory: Conditional probability, Bayes rule, conditional expectations.
2. Homeworks/programs will be assigned bi-weekly. If you do not have any prior numerical computing experience, I suggest you use MATLAB for the programs.
3. First Midterm will be given approximately at the middle of the semester and the second will be in the last week of classes.
4. Students must choose a project within the first six weeks. Students will be given considerable latitude to choose their projects. A project demonstration is due at the end of the semester.
5. A set of informal notes which will evolve with the course can be found here.
   

   
   

Supervised Learning: linear discriminants, the perceptron, backpropagation, multi-layer perceptrons, radial basis functions, learning and generalization theory, support vector machines.

Mixture Modeling: mixtures, the expectation-maximization (EM) algorithm, modular networks.

Mean Field Theory: Ising model, naive mean field approximation, deterministic annealing, combinatorial optimization, Boltzmann machines.

Unsupervised Learning: competitive networks, clustering, Kohonen self-organizing feature maps, Hebbian learning, principal and independent component analysis (PCA and ICA).