dc.contributor.author | Engel, Alejandro | en_US |
dc.date.accessioned | 2007-10-24T02:04:49Z | en_US |
dc.date.available | 2007-10-24T02:04:49Z | en_US |
dc.date.issued | 2001 | en_US |
dc.identifier.citation | Kybernetes 30N9-10 (2001) 1192-1198 | en_US |
dc.identifier.issn | 0368-492X | en_US |
dc.identifier.uri | http://hdl.handle.net/1850/5139 | en_US |
dc.description | RIT community members may access full-text via RIT Libraries licensed databases: http://library.rit.edu/databases/ | |
dc.description.abstract | The area of artificial neural networks, which dates back to the early twentieth century, could only offer positive contributions to technology after the back-propagation algorithm was proposed in 1986. In this note an alternative algorithm to the gradient descent used in back-propagation is proposed. This algorithm is based on the discrete central difference. This procedure, as opposed to the back-propagation algorithm, offers the possibility of true parallel computation. | en_US |
dc.description.sponsorship | To the memory of Oskar Bratter. This research was partially supported by a Rochester Institute of Technology, College of Science, Dean’s Summer Research Grant. | en_US |
dc.language.iso | en_US | en_US |
dc.publisher | Emerald Group Publishing Limited | en_US |
dc.relation.ispartofseries | vol. 30 | en_US |
dc.relation.ispartofseries | no. 9-10 | en_US |
dc.subject | Algorithms | en_US |
dc.subject | Cybernetics | en_US |
dc.subject | Neural networks | en_US |
dc.subject | Parallel computing | en_US |
dc.title | True parallel processing in artificial neural networks | en_US |
dc.type | Article | en_US |
dc.identifier.url | http://dx.doi.org/10.1108/03684920110405764 | |