Neural Network Models

Introduction:-There is a tremendous variety of neural network models. Some are variants or improvements of the types already presented-MLP, ART, SOM, associative memories. Other connectionist models emerge and evolve with the development of knowledge about the way real neurons work. Neural networkmodels may differ in the following points:

1.The type of neurons used and type of calculations.

2. The mathematical model used for representing and processing of information in the network (algebraic, statistical, fuzzy, etc.). This includes methods of training and recall, convergence and equilibrium properties, etc.

3. The class of problems they are designed to solve (classification, optimization, pattern association, etc.).

A neural network model may be a hybrid between two connectionist models, for example, a model implementing competitive learning and a model for supervised learning.