A comparison of architectural alternatives for recurrent networks Wilson, William Hulme en_US 2021-11-25T13:11:02Z 2021-11-25T13:11:02Z 1993 en_US
dc.description.abstract This paper describes a class of recurrent neural networks related to Elman networks. The networks used herein differ from standard Elman networks in that they may have more than one state vector. Such networks have an explicit representation of the hidden unit activations from several steps back. In principle, a single-state-vector network is capable of learning any sequential task that a multi-state-vector network can learn. This paper describes experiments which show that, in practice, and for the learning task used, a multi-state-vector network can learn a task faster and better than a single-state-vector network. The task used involved learning the graphotactic structure of a sample of about 400 English words. en_US
dc.language English
dc.language.iso EN en_US
dc.publisher Sydney University Electrical Engineering en_US
dc.rights CC BY-NC-ND 3.0 en_US
dc.rights.uri en_US
dc.source Legacy MARC en_US
dc.subject.other Neural Networks, Genetic Algorithms and Fuzzy Logic (280212) en_US
dc.subject.other Elman network en_US
dc.subject.other simple recurrent network en_US
dc.subject.other tower network en_US
dc.title A comparison of architectural alternatives for recurrent networks en_US
dc.type Conference Paper en
dcterms.accessRights open access
dspace.entity.type Publication en_US
unsw.description.notePublic Further publications of this author may be found at en_US
unsw.identifier.doi Sydney, Australia en_US
unsw.relation.faculty Engineering
unsw.relation.ispartofconferenceLocation Sydney, Australia en_US
unsw.relation.ispartofconferenceName Australian Conference on Neural Networks en_US
unsw.relation.ispartofconferenceProceedingsTitle Proceedings of the Fourth Australian Conference on Neural Networks (ACNN’93) en_US
unsw.relation.ispartofconferenceYear 1993 en_US
unsw.relation.ispartofpagefrompageto 189-192 en_US
unsw.relation.originalPublicationAffiliation Wilson, William Hulme, Computer Science & Engineering, Faculty of Engineering, UNSW en_US School of Computer Science and Engineering *
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
peer-reviewed postprint.pdf
50.18 KB
Resource type