Analysis of Bidirectional Associative Memory using Self-consistent Signal to Noise Analysis and Statistical Neurodynamics
Year: 2004
Type: article
Abstract: Bidirectional associative memory (BAM) is a kind of an artificial neural network used to memorize and retrieve heterogeneous pattern pairs. Many efforts have been made to improve BAM from the the viewpoint of computer application, and few theoretical studies have been done. We investigated the theoretical characteristics of BAM using a framework of statistical-mechanical analysis. To investigate the equilibrium state of BAM, we applied self-consistent signal to noise analysis (SCSNA) and obtained a macroscopic parameter equations and relative capacity. Moreover, to investigate not only the equilibrium state but also the retrieval process of reaching the equilibrium state, we applied statistical neurodynamics to the update rule of BAM and obtained evolution equations for the macroscopic parameters. These evolution equations are consistent with the results of SCSNA in the equilibrium state.
DOI: 10.1143/jpsj.73.2406
Authors: Hayaru Shouno, Shoji Kido, Masato Okada
Institutions: Yamaguchi University, RIKEN Center for Brain Science, RIKEN
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1528866341