| This course is intended as an introduction to some of the more popular neural network paradigms; the paradigms discussed will include both feedforward and feedback structures as well as both supervised and unsupervised training algorithms. Emphasis will be placed on the engineering aspects of these systems as opposed to their biological plausibility. A large percentage of the course will be devoted to the theory which underlies the paradigms; applications will also be discussed. From this course, students should gain an appreciation for gradient descent and other optimization algorithms, higher dimensional geometry, multivariate calculus. |
