Construction of neural network classification expert systems using switching theory algorithms

Abstract

A new family of neural network (NN) architectures is presented. This family of architectures solves the problem of constructing and training minimal NN classification expert systems by using switching theory. The primary insight that leads to the use of switching theory is that the problem of minimizing the number of rules and the number of IF statements (antecedents) per rule in a NN expert system can be recast into the problem of minimizing the number of digital gates and the number of connections between digital gates in a VLSI circuits. The rules that the NN generates to perform a task are readily extractable from the network's weights and topology. Analysis and simulations on the Mushroom database illustrate the system's performance.<>