Show simple item record

dc.contributor.authorFausett, Laurene V
dc.date.accessioned2017-10-06T16:48:12Z
dc.date.available2017-10-06T16:48:12Z
dc.date.issued1996-03-22
dc.identifier.citationFausett, L. V. (1996). Similarity-based learning for pattern classification. Paper presented at the Proceedings of SPIE - the International Society for Optical Engineering, , 2760 26-35.en_US
dc.identifier.urihttp://hdl.handle.net/11141/1783
dc.descriptionArtificial neural networks, Pattern classification, Similarity-based learning, Unsupervised learningen_US
dc.description.abstractSeveral standard neural networks, including counterpropagation networks, predictive ART networks, and radial basis function networks, are based on a combination of clustering (unsupervised learning) and mapping (supervised learning). A comparison of the characteristics of these networks for pattern classification problems is presented.en_US
dc.language.isoen_USen_US
dc.rightsThis published article is made available in accordance with publishers policy. It may be subject to U.S. copyright law.en_US
dc.rights.urihttp://spie.org/publications/journals/guidelines-for-authors#Terms_of_Useen_US
dc.titleSimilarity-based learning for pattern classificationen_US
dc.typeConference Proceedingen_US
dc.identifier.doi10.1117/12.235944


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record