6EC6.1-NEURAL NETWORKS |
Units: I-INTRODUCTION: |
Introduction to Neural Networks, Biological basis for NN, Human brain, Models
of a Neuron, Directed Graphs, Feedback, Network architectures, Knowledge representation, Artificial
intelligence & Neural Networks.
|
Units: II-LEARNING PROCESSES: |
Introduction, Error –Correction learning, Memory –based learning,
Hebbian learning, Competitive learning, Boltzmann learning, Learning with a Teacher & without a teacher,
learning tasks, Memory, Adaptation. |
Units: III-SINGLE LAYER PERCEPTRONS: |
Introduction, Least-mean-square algorithm, Learning Curves,
Learning rate Annealing Techniques, Perceptron, Perceptron Convergence Theorem.
|
Units: IV-MULTI LAYER PERCEPTRONS: |
Introduction, Back-Propagation Algorithm, XOR Problem,
Output representation and Decision rule, Feature Detection, Back-Propagation and Differentiation,
Hessian Matrix, Generalization.
|
Units: V-RADIAL-BASIS FUNCTION NETWORKS & SELF-ORGANISING MAPS: |
Introduction to Radial
basis function networks, Cover’s Theorem on the Separability of Patterns, Interpolation Problem,
Generalized Radial-Basis function networks, XOR Problem. Self-Organizing map, Summary of SOM
Algorithm, Properties of the feature map.
|
|