Perceptron-how this neural network model lets you evaluate Booleanfunctions |
| |
Authors: | Johnson ML |
| |
Affiliation: | Dept. of Comput. Sci., Stanford Univ., CA; |
| |
Abstract: | The author explores aspects of just what a neural network can do, by building a simple model that evaluates Boolean functions. The neural network model for the system that the author is building is one of the earliest: the perceptron, developed by Rosenblatt in the 1960s. The goal of the present work is to build a perceptron that can evaluate Boolean functions by learning the input patterns and the associated output. A major part of the process of building a neural net, the training of the network, is discussed. A wide variety of training algorithms have been developed. An analysis of the system is given, and limitations of the perceptron are described |
| |
Keywords: | |
|
|