Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/3529
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | BOUTEN, Marcus | - |
dc.contributor.author | SCHIETSE, J | - |
dc.contributor.author | VAN DEN BROECK, Christian | - |
dc.date.accessioned | 2007-11-28T17:03:22Z | - |
dc.date.available | 2007-11-28T17:03:22Z | - |
dc.date.issued | 1995 | - |
dc.identifier.citation | PHYSICAL REVIEW E, 52(2). p. 1958-1967 | - |
dc.identifier.issn | 1063-651X | - |
dc.identifier.uri | http://hdl.handle.net/1942/3529 | - |
dc.description.abstract | We present a streamlined formalism which reduces the calculation of the generalization error for a perceptron, trained on random examples generated by a teacher perceptron, to a matter of simple algebra. The method is valid whenever the student perceptron can be identified as the unique minimum of a specific cost function. The asymptotic generalization error is calculated explicitly for a broad class of cost functions, and a specific cost function is singled out that leads to a generalization error extremely close to the one of the Bayes classifier. | - |
dc.language.iso | en | - |
dc.publisher | AMERICAN PHYSICAL SOC | - |
dc.title | Gradient descent learning in perceptrons - A review of its possibilities | - |
dc.type | Journal Contribution | - |
dc.identifier.epage | 1967 | - |
dc.identifier.issue | 2 | - |
dc.identifier.spage | 1958 | - |
dc.identifier.volume | 52 | - |
local.format.pages | 10 | - |
dc.description.notes | BOUTEN, M, LIMBURGS UNIV CENTRUM,UNIV CAMPUS,B-3590 DIEPENBEEK,BELGIUM. | - |
local.type.refereed | Refereed | - |
local.type.specified | Article | - |
dc.bibliographicCitation.oldjcat | A1 | - |
dc.identifier.doi | 10.1103/PhysRevE.52.1958 | - |
dc.identifier.isi | A1995RQ37700082 | - |
item.contributor | BOUTEN, Marcus | - |
item.contributor | SCHIETSE, J | - |
item.contributor | VAN DEN BROECK, Christian | - |
item.fulltext | No Fulltext | - |
item.fullcitation | BOUTEN, Marcus; SCHIETSE, J & VAN DEN BROECK, Christian (1995) Gradient descent learning in perceptrons - A review of its possibilities. In: PHYSICAL REVIEW E, 52(2). p. 1958-1967. | - |
item.accessRights | Closed Access | - |
Appears in Collections: | Research publications |
SCOPUSTM
Citations
27
checked on Aug 25, 2025
WEB OF SCIENCETM
Citations
25
checked on Aug 25, 2025
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.