Reducing the active paths interference in the Chialvo-Bak “Minibrain” Model
Reducing the active paths interference in the Chialvo-Bak “Minibrain” Model
We examine a simple biologically-motivated neural network, the version of the Chialvo-Bak “minibrain”, and propose an approach to decrease the negative effect of the active paths interferences in a process of learning new data. For this purpose we use randomly ordered neural network structure with recurrent signal propagation mode. We investigated the network's performance and learning capacity dependence on its nodes' interconnection level. Our simulation study shows that the proposed approach needs on average 40% less number of learning steps for learning the same set of patterns and has higher learning capacity compared to the existing method.
734-737
Kulakov, Anton
274cbc43-2cab-495c-910b-1a64cec81df6
Zwolinski, Mark
adfcb8e7-877f-4bd7-9b55-7553b6cb3ea0
7 January 2011
Kulakov, Anton
274cbc43-2cab-495c-910b-1a64cec81df6
Zwolinski, Mark
adfcb8e7-877f-4bd7-9b55-7553b6cb3ea0
Kulakov, Anton and Zwolinski, Mark
(2011)
Reducing the active paths interference in the Chialvo-Bak “Minibrain” Model.
International Journal of Modeling and Optimization, 2 (6), .
(doi:10.7763/IJMO.2012.V2.222).
Abstract
We examine a simple biologically-motivated neural network, the version of the Chialvo-Bak “minibrain”, and propose an approach to decrease the negative effect of the active paths interferences in a process of learning new data. For this purpose we use randomly ordered neural network structure with recurrent signal propagation mode. We investigated the network's performance and learning capacity dependence on its nodes' interconnection level. Our simulation study shows that the proposed approach needs on average 40% less number of learning steps for learning the same set of patterns and has higher learning capacity compared to the existing method.
This record has no associated files available for download.
More information
Published date: 7 January 2011
Additional Information:
Event Dates: January 2011
Venue - Dates:
3rd International Conference on Computer Modeling and Simulation (ICCMS 2011), Mumbai, India, 2011-01-01
Organisations:
EEE
Identifiers
Local EPrints ID: 272392
URI: http://eprints.soton.ac.uk/id/eprint/272392
ISSN: 2010-3697
PURE UUID: 4d02dec7-f83e-432d-8175-15aeb7df9d2c
Catalogue record
Date deposited: 01 Jun 2011 13:29
Last modified: 15 Mar 2024 02:39
Export record
Altmetrics
Contributors
Author:
Anton Kulakov
Author:
Mark Zwolinski
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