Open AccessA novel neural network for associative memory via dynamical systems
Author(s) -
KL Mak,
Jigen Peng,
Zong Ben Xu,
Ka Fai Cedric Yiu
Publication year - 2006
Publication title -
discrete and continuous dynamical systems. series b
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.864
H-Index - 53
eISSN - 1553-524X
pISSN - 1531-3492
DOI - 10.3934/dcdsb.2006.6.573
Subject(s) - forgetting , content addressable memory , bidirectional associative memory , artificial neural network , computer science , spurious relationship , associative property , matrix (chemical analysis) , connection (principal bundle) , content addressable storage , recurrent neural network , artificial intelligence , machine learning , mathematics , linguistics , materials science , geometry , pure mathematics , composite material , philosophy
This paper proposes a novel neural network model for associative memory using dynamical systems. The proposed model is based on synthesizing the external input vector, which is different from the conventional approach where the design is based on synthesizing the connection matrix. It is shown that this new neural network (a) stores the desired prototype patterns as asymptotically stable equilibrium points, (b) has no spurious states, and (c) has learning and forgetting capabilities. Moreover, new learning and forgetting algorithms are also developed via a novel operation on the matrix space. Numerical examples are presented to illustrate the effectiveness of the proposed neural network for associative memory. Indeed, results of simulation experiments demonstrate that the neural network is effective and can be implemented easily.link_to_subscribed_fulltex