<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=undefined&type=result"></script>');
-->
</script>

COPY SCRIPT

For further information contact us at helpdesk@openaire.eu

Function approximation with spiked random networks

descriptionPublicationkeyboard_double_arrow_right Article 01 Jan 1999 United States Publisher:Institute of Electrical and Electronics Engineers (IEEE)Journal:IEEE Transactions on Neural Networks, volume 10, pages 3-9 (issn: 1045-9227,

Authors: Gelenbe, Erol; Mao, Zhi-Hong; Da-Li, Yan;

doi: 10.1109/72.737488

pmid: 18252498

Function approximation with spiked random networks

- Summary
- Subjects
- Related research
  (14)
- Metrics

Abstract

This paper examines the function approximation properties of the "random neural-network model" or GNN. The output of the GNN can be computed from the firing probabilities of selected neurons. We consider a feedforward Bipolar GNN (BGNN) model which has both "positive and negative neurons" in the output layer, and prove that the BGNN is a universal function approximator. Specifically, for any f is an element of C([0, 1]s) and any epsilon>0, we show that there exists a feedforward BGNN which approximates f uniformly with error less than epsilon. We also show that after some appropriate clamping operation on its output, the feedforward GNN is also a universal function approximator.

Country

United States

Related Organizations

Tsinghua University
China (People's Republic of)
Institute of Theoretical and Applied Informatics
Poland
University of Central Florida
United States
University of Pittsburgh
United States
Polish Academy of Sciences
Poland

View all View all

Keywords

Function Approximation, Theory & Methods, Function approximation random neural networks, NEURAL NETWORKS, Engineering, Artificial Intelligence, Hardware &, Computer Science, Architecture, Spiked neural networks, Constructive Proof, Electrical & Electronic, COMPRESSION, Random Neural Network, Continuous and Bounded Functions, spiked neural networks, function approximation random neural networks

14 Research products, page of 2

Impact byBIP!

	citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	89
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Top 10%
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Top 10%
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Top 10%