Learning in a Neural Network

Neural Networks Module

The module below can be covered in a three week period in the Introduction to AI Course

Brief History of Neural Networks
Definition of a Neural Network
Learning in a Neural Network
The Pattern Associator
The Hebb Rule
The Delta Rule
The Generalized Delta Rule

This module on Neural Networks was written by Ingrid Russell of the University of Hartford . It is being printed with permission from Collegiate Microcomp uter Journal.

If you have any comments or suggestions, please send email to irussell@mail.hartford.edu

Learning in a Neural Network

Learning is essential to most of these neural network architectures and hence the choice of a learning algorithm is a central issue in network development. What is really meant by saying that a processing element learns? Learning implies that a processing unit is capable of changing its input/output behavior as a result of changes in the environment. Since the activation rule is usually fixed when the network is constructed and since the input/output vector cannot be changed, to change the input/output behavior the weights corresponding to that input vector need to be adjusted. A method is thus needed by which, at least during a training stage, weights can be modified in response to the input/output process. A number of such learning rules are available for neural network models. In a neural network, learning can be supervised, in which the network is provided with the correct answer for the output during training, or unsupervised, in which no external teacher is present.