The University of Southampton
University of Southampton Institutional Repository

Stochastic Connection Neural Networks

Stochastic Connection Neural Networks
Stochastic Connection Neural Networks
We investigate a novel neural network model which uses stochastic weights. It is shown that the functionality of the network is comparable to that of a general stochastic neural network using standard sigmoid activation functions. For the multilayer feedforward structure we demonstrate the network can be successfully used to solve a real problem like handwritten digit recognition. It is also shown that the recurrent network is as powerful as a Boltzmann machine. A new technique to implement simulated annealing is presented. Simulation results on the graph bisection problem demonstrate the model is efficient for global optimization.
0 85296 641 5
35-39
IET Conference Publications
Zhao, Jieyu
2b47e359-c555-4247-89ee-d8430700d658
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b
Zhao, Jieyu
2b47e359-c555-4247-89ee-d8430700d658
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b

Zhao, Jieyu and Shawe-Taylor, John (1995) Stochastic Connection Neural Networks. In Proceedings of the Fourth IEE Conference on Artificial Neural Networks. IET Conference Publications. pp. 35-39 . (doi:10.1049/cp:19950525).

Record type: Conference or Workshop Item (Paper)

Abstract

We investigate a novel neural network model which uses stochastic weights. It is shown that the functionality of the network is comparable to that of a general stochastic neural network using standard sigmoid activation functions. For the multilayer feedforward structure we demonstrate the network can be successfully used to solve a real problem like handwritten digit recognition. It is also shown that the recurrent network is as powerful as a Boltzmann machine. A new technique to implement simulated annealing is presented. Simulation results on the graph bisection problem demonstrate the model is efficient for global optimization.

This record has no associated files available for download.

More information

Published date: 1995
Venue - Dates: Fourth International Conference on Artificial Neural Networks, Cambridge, UK, 1995-06-26 - 1995-06-28
Organisations: Electronics & Computer Science

Identifiers

Local EPrints ID: 259685
URI: http://eprints.soton.ac.uk/id/eprint/259685
ISBN: 0 85296 641 5
PURE UUID: 7c1e54dc-d363-4cb5-9232-0a547c1c8f78

Catalogue record

Date deposited: 05 Aug 2004
Last modified: 14 Mar 2024 06:27

Export record

Altmetrics

Contributors

Author: Jieyu Zhao
Author: John 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

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.

×