The University of Southampton
×
Filter your search:
University of Southampton Institutional Repository

Emergent activation functions from a stochastic bit stream neuron

Emergent activation functions from a stochastic bit stream neuron
Emergent activation functions from a stochastic bit stream neuron
In this paper we present the results of experimental work that demonstrates the generation of linear and sigmoid activation functions in a digital stochastic bit-stream neuron. These activation functions are generated by a stochastic process and require no additional hardware, allowing the design of an individual neuron to be extremely compact.
0013-5194
331-333
Daalen, M.
f49a9ae4-bea1-4263-9f23-92835c39fa66
Kosel, T.
3d370553-8738-4eeb-9652-c36167b503e1
Jeavons, P.
bf271c75-e9a7-413c-8bd5-3f5d3ead0de1
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db
Daalen, M.
f49a9ae4-bea1-4263-9f23-92835c39fa66
Kosel, T.
3d370553-8738-4eeb-9652-c36167b503e1
Jeavons, P.
bf271c75-e9a7-413c-8bd5-3f5d3ead0de1
Shawe-Taylor, J.
c32d0ee4-b422-491f-8c28-78663851d6db

Daalen, M., Kosel, T., Jeavons, P. and Shawe-Taylor, J. (1994) Emergent activation functions from a stochastic bit stream neuron. Electronics Letters, 30 (4), 331-333.

Record type: Article

Abstract

In this paper we present the results of experimental work that demonstrates the generation of linear and sigmoid activation functions in a digital stochastic bit-stream neuron. These activation functions are generated by a stochastic process and require no additional hardware, allowing the design of an individual neuron to be extremely compact.

Text
EmergentActivationFunctionsFromAStochasticBitStreamNeuron.pdf - Other
Download (95kB)

More information

Published date: February 1994
Related URLs:
Organisations: Electronics & Computer Science
Learn more about Electronics & Computer Science research

Identifiers

Local EPrints ID: 259815
URI: http://eprints.soton.ac.uk/id/eprint/259815
ISSN: 0013-5194
PURE UUID: 2b59eded-157c-4d89-b87f-10cc047a3779

Catalogue record

Date deposited: 24 Aug 2004
Last modified: 14 Mar 2024 06:28

Export record

Contributors

Author: M. Daalen
Author: T. Kosel
Author: P. Jeavons
Author: J. Shawe-Taylor

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Library staff additional information
Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×