Document Type

Report

Date

6-15-1993

Keywords

Neural network theory, Dynamical Systems, Approximation Theory

Language

English

Disciplines

Computer Sciences

Description/Abstract

Networks with sigmoid node functions have been shown to be universal approximators, and can use straightforward implementations of learning algorithms. Mathematically, what is common to different sigmoid functions used by different researchers? We establish a common representation of inverse sigmoid functions in terms of the Guass Hypergeometric function, generalizing different node function formulations. We also show that the continuous Hopfield network equation can be transformed into a Legendre differential equation, without assuming the specific form of the node function; this establishes a link between Hopfield nets and the method of function approximation using Legendre polynomials

Additional Information

School of Computer and Information Science, Syracuse University, SU-CIS-93-27

Source

local

Share

COinS
 
 

To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.