Presentation 2005-12-16
On the recalling rate of Morphological Associative Memory
Ke ZHANG, Sadayuki MURASHIMA, Takayasu FUCHIDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Morphological associative memory is obtained by replacing the sum of product of input signals by Maximum or Minimum operation. Ritter presented a procedure of associative memory which utilizes associative memory matrix M and W, sophisticatedly. In this paper we derived the recalling rate of associative memory. The recalling rates depend on the stored patterns and their kernels. We discussed the basis of recalling rates and showed that the recalling rate coincides with the experimental data. We will also derive the recalling rate of our newly presented procedure in which everything is reverse from Ritter's recalling process. If the number of stored patterns is 5, recalling rate is found out to be the highest when every kernel consists of 2 fired pixel. If the number of noise bits is constant it is found out that the bigger the pattern size is and the higher the recalling rate is.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Morphological associative memory / recalling rate / kernel / recalling process
Paper # NLP2005-86
Date of Issue

Conference Information
Committee NLP
Conference Date 2005/12/9(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On the recalling rate of Morphological Associative Memory
Sub Title (in English)
Keyword(1) Morphological associative memory
Keyword(2) recalling rate
Keyword(3) kernel
Keyword(4) recalling process
1st Author's Name Ke ZHANG
1st Author's Affiliation Ricoh Software Inc.()
2nd Author's Name Sadayuki MURASHIMA
2nd Author's Affiliation Faculty of Engineering, kagoshima University
3rd Author's Name Takayasu FUCHIDA
3rd Author's Affiliation Faculty of Engineering, kagoshima University
Date 2005-12-16
Paper # NLP2005-86
Volume (vol) vol.105
Number (no) 483
Page pp.pp.-
#Pages 6
Date of Issue