New results of quick learning for bidirectional associative memory having high capacity

Motonobu Hattori, Masafumi Hagiwara, Masao Nakagawa

Research output: Contribution to conferencePaper

5 Citations (Scopus)

Abstract

Several important characteristics of Quick Learning for Bidirectional Associative Memory (QLBAM) are introduced. QLBAM uses two stages learning. In the first stage, the BAM is trained by Hebbian learning and then by Pseudo-Relaxation Learning Algorithm for BAM (PRLAB). The following features of the QLBAM are made clear: 1) it is insensitive to correlation of training pairs; 2) it is robust for noisy inputs; 3) the minimum absolute value of net inputs indexes a noise margin; 4) the memory capacity is greatly improved: the maximum capacity in our simulation is about 2.2N.

Original languageEnglish
Pages1080-1085
Number of pages6
Publication statusPublished - 1994 Dec 1
EventProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7) - Orlando, FL, USA
Duration: 1994 Jun 271994 Jun 29

Other

OtherProceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7)
CityOrlando, FL, USA
Period94/6/2794/6/29

ASJC Scopus subject areas

  • Software

Fingerprint Dive into the research topics of 'New results of quick learning for bidirectional associative memory having high capacity'. Together they form a unique fingerprint.

  • Cite this

    Hattori, M., Hagiwara, M., & Nakagawa, M. (1994). New results of quick learning for bidirectional associative memory having high capacity. 1080-1085. Paper presented at Proceedings of the 1994 IEEE International Conference on Neural Networks. Part 1 (of 7), Orlando, FL, USA, .