Node Structure and Training

Abstract

In this chapter the basic node structure and node training algorithm used in the model are developed. In the current model, the basic node is a Threshold Logic Unit (TLU), or more specifically, a Linear Threshold Unit (LTU). The standard LTU is a thresholded linear equation that is used for the binary categorization of feature patterns. The primary learning process for a node is the perceptron training algorithm. Although neither the representation nor the training strategy is explicitly biological, an LTU is a standard (simplified) model of neural computation, and perceptron training is sufficiently similar to classical conditioning to be of interest. Possible neural mechanisms for perceptron training have been worked out to a considerable extent. Both the node representation and the training algorithm are sufficiently simple to permit a significant amount of analysis. Variations on the basic model are considered and possible extensions to deal with continuous input values are explored.