Show simple item record

Files in this item


Item metadata

dc.contributor.advisorWeir, Michael
dc.contributor.authorPolhill, John Gareth
dc.coverage.spatialix, 356 p.en_US
dc.description.abstractNeural networks need to be able to guarantee their intrinsic generalisation abilities if they are to be used reliably. Mitchell's concept and version spaces technique is able to guarantee generalisation in the symbolic concept-learning environment in which it is implemented. Generalisation, according to Mitchell, is guaranteed when there is no alternative concept that is consistent with all the examples presented so far, except the current concept, given the bias of the user. A form of bidirectional convergence is used by Mitchell to recognise when the no-alternative situation has been reached. Mitchell's technique has problems of search and storage feasibility in its symbolic environment. This thesis aims to show that by evolving the technique further in a neural environment, these problems can be overcome. Firstly, the biasing factors which affect the kind of concept that can be learned are explored in a neural network context. Secondly, approaches for abstracting the underlying features of the symbolic technique that enable recognition of the no-alternative situation are discussed. The discussion generates neural techniques for guaranteeing generalisation and culminates in a neural technique which is able to recognise when the best fit neural weight state has been found for a given set of data and topology.en_US
dc.publisherUniversity of St Andrews
dc.subject.lcshNeural networks (Computer science)en
dc.titleGuaranteeing generalisation in neural networksen_US
dc.contributor.sponsorEngineering and Physical Sciences Research Council (EPSRC)en_US
dc.type.qualificationnamePhD Doctor of Philosophyen_US
dc.publisher.institutionThe University of St Andrewsen_US

This item appears in the following Collection(s)

Show simple item record