首页 | 官方网站   微博 | 高级检索  
     


Fast retraining of SDM
Authors:V G Tul’chinskii  I N Pshonkovskaya  S V Zaytseva
Affiliation:(1) Cybernetics Institute, National Academy of Sciences of Ukraine, Kiev, Ukraine
Abstract:The functioning of Kanerva’s Sparse Distributed Memory is examined under conditions of changes in data that are to be written at an address. To improve the efficiency of retraining, a modification of the Kanerva writing procedure is proposed. Translated from Kibernetika i Sistemnyi Analiz, No. 4, pp. 40–49, July–August, 1999.
Keywords:simulation of functions of the natural memory  representation of data by binary vectors  Kanerva s Sparse Distributed Memory (SDM)  algorithms of processing SDM  retraining of SDM
本文献已被 SpringerLink 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号