完整後設資料紀錄
DC 欄位語言
dc.contributor.authorCHENG, CJen_US
dc.contributor.authorYEH, PCen_US
dc.contributor.authorHSU, KYen_US
dc.date.accessioned2014-12-08T15:03:50Z-
dc.date.available2014-12-08T15:03:50Z-
dc.date.issued1994-09-01en_US
dc.identifier.issn0740-3224en_US
dc.identifier.urihttp://dx.doi.org/10.1364/JOSAB.11.001619en_US
dc.identifier.urihttp://hdl.handle.net/11536/2363-
dc.description.abstractWe consider the properties of a generalized perceptron learning network, taking into account the decay or the gain of the weight vector during the training stages. A mathematical proof is given that shows the conditional convergence of the learning algorithm. The analytical result indicates that the upper bound of the training steps is dependent on the gain (or decay) factor. A sufficient condition of exposure time for convergence of a photorefractive perceptron network is derived. We also describe a modified learning algorithm that provides a solution to the problem of weight vector decay in an optical perceptron caused by hologram erasure. Both analytical and simulation results are presented and discussed.en_US
dc.language.isoen_USen_US
dc.titleGENERALIZED PERCEPTRON LEARNING RULE AND ITS IMPLICATIONS FOR PHOTOREFRACTIVE NEURAL NETWORKSen_US
dc.typeArticleen_US
dc.identifier.doi10.1364/JOSAB.11.001619en_US
dc.identifier.journalJOURNAL OF THE OPTICAL SOCIETY OF AMERICA B-OPTICAL PHYSICSen_US
dc.citation.volume11en_US
dc.citation.issue9en_US
dc.citation.spage1619en_US
dc.citation.epage1624en_US
dc.contributor.department交大名義發表zh_TW
dc.contributor.department光電工程學系zh_TW
dc.contributor.departmentNational Chiao Tung Universityen_US
dc.contributor.departmentDepartment of Photonicsen_US
dc.identifier.wosnumberWOS:A1994PE85300011-
dc.citation.woscount1-
顯示於類別:期刊論文


文件中的檔案:

  1. A1994PE85300011.pdf

若為 zip 檔案,請下載檔案解壓縮後,用瀏覽器開啟資料夾中的 index.html 瀏覽全文。