Improving neural network performance by adapting node nonlinearities

Frans M. Coetzee; Virginia L. Stonick

doi:10.1117/12.130830

16 December 1992 Improving neural network performance by adapting node nonlinearities

Frans M. Coetzee, Virginia L. Stonick

Proceedings Volume 1766, Neural and Stochastic Methods in Image and Signal Processing; (1992) https://doi.org/10.1117/12.130830
Event: San Diego '92, 1992, San Diego, CA, United States

Abstract

It is known that using an infinite number of hidden layer nodes feedforward neural networks can approximate any continuous function with compact support arbitrarily well using very simple node nonlinearities. We investigate whether network architectures can be found that use more complicated node nonlinearities to achieve better approximation using a restricted number of nodes. Two methods are proposed, one based on modifying standard backpropagation networks, and one based on Kolmogorov's theorem. The feasibility of these networks is evaluated by considering their performance when predicting chaotic time series and memorizing the XOR mapping.

Citation Download Citation

Frans M. Coetzee and Virginia L. Stonick "Improving neural network performance by adapting node nonlinearities", Proc. SPIE 1766, Neural and Stochastic Methods in Image and Signal Processing, (16 December 1992); https://doi.org/10.1117/12.130830

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available