Analysis of the Mean Field Annealing Algorithm for Graph Colouring
Analysis of the Mean Field Annealing Algorithm for Graph Colouring
We introduce the Multi State Bitstream Neuron. By replacing the stochastic activation function with stochastic weights the MSBSN is shown to approximate a Generalised Boltzmann Machine. Benchmarks show the algorithm performs as well as the Boltzmann algorithm whilst the MSBSN lends itself to a very compact and fast hardware implementation.
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b
Zerovnik, Janez v
aa969d58-9af1-4dff-9910-92d99a326709
1993
Shawe-Taylor, John
b1931d97-fdd0-4bc1-89bc-ec01648e928b
Zerovnik, Janez v
aa969d58-9af1-4dff-9910-92d99a326709
Shawe-Taylor, John and Zerovnik, Janez v
(1993)
Analysis of the Mean Field Annealing Algorithm for Graph Colouring
Record type:
Monograph
(Project Report)
Abstract
We introduce the Multi State Bitstream Neuron. By replacing the stochastic activation function with stochastic weights the MSBSN is shown to approximate a Generalised Boltzmann Machine. Benchmarks show the algorithm performs as well as the Boltzmann algorithm whilst the MSBSN lends itself to a very compact and fast hardware implementation.
Text
CSD-TR-93-13.pdf
- Other
More information
Published date: 1993
Organisations:
Electronics & Computer Science
Identifiers
Local EPrints ID: 259754
URI: http://eprints.soton.ac.uk/id/eprint/259754
PURE UUID: 4bb5d4b7-5ded-4794-a10a-662bd6752481
Catalogue record
Date deposited: 12 Aug 2004
Last modified: 14 Mar 2024 06:28
Export record
Contributors
Author:
John Shawe-Taylor
Author:
Janez v Zerovnik
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