Statistical neurodynamics of associative memory

✍ Scribed by Shun-Ichi Amari; Kenjiro Maginu

• Publisher: Elsevier Science
• Year: 1988
• Tongue: English
• Weight: 854 KB
• Volume: 1
• Category: Article
• ISSN: 0893-6080
• DOI: 10.1016/0893-6080(88)90022-6

✦ Synopsis

A new statistical neurodynamical method is proposed Jor ana(vzing the non-equilibrium dynamical behaviors of an autocorrelation associative memor), model. The theory explains strange dynamical behaviors in recalling processes which are observed by computer simulations: Starting with an initial state close to a memorized pattern, the state monotonically approaches the memorized one. Starting with an initial state which is not so close to a memorized one, the state once approaches it but then goes awayjkom it. The theory not only gives the relative and absolute capacity of the memory network without using the spin glass analogy, but it explains the non-equilibrium or transient dynamical behaviors oJthe recalling process by taking the hmg-term correlation effects into account. It thus explains the strange behaviors due to strange shapes of the basins Of attractors.