dc.contributor.author | Townsend, J | |
dc.contributor.author | Keedwell, EC | |
dc.contributor.author | Galton, A | |
dc.date.accessioned | 2016-03-31T09:15:18Z | |
dc.date.issued | 2013-08-03 | |
dc.description.abstract | SHRUTI is a model of how predicate relations can
be represented and reasoned upon using a network
of spiking neurons, attempting to model the brain’s
ability to perform reasoning using as biologically
plausible a means as possible. This paper extends
the biological plausibility of the SHRUTI model
by presenting a genotype representation of connections
in a SHRUTI network using indirect encoding
and showing that working networks represented
in this way can be produced through an evolutionary
process. A multi-objective algorithm is used
to minimise the error and the number of weight
changes that take place as a network learns | en_GB |
dc.identifier.citation | Proceedings of the 9th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy13), pp. 56-61 | en_GB |
dc.identifier.uri | http://hdl.handle.net/10871/20891 | |
dc.language.iso | en | en_GB |
dc.publisher | Neural-Symbolic Learning and Reasoning | en_GB |
dc.relation.url | http://www.neural-symbolic.org/NeSy13/ | en_GB |
dc.relation.url | http://daselab.cs.wright.edu/nesy/NeSy13/townsend.pdf | en_GB |
dc.rights | This is the final version of the article. Available from Neural-Symbolic Learning and Reasoning via the link in this record. | en_GB |
dc.title | Evolution of connections in SHRUTI networks | en_GB |
dc.type | Conference paper | en_GB |
dc.date.available | 2016-03-31T09:15:18Z | |