Analysis of Bidirectional Associative Memory using SCSNA and Statistical Neurodynamics

スポンサーリンク

概要

• 論文の詳細を見る

• Macroscopic properties of a bidirectional associative memory (BAM) are studied within a framework of S/N analysis called SCSNA. We obtained the relative capacity, which means the relative number of pattern pairs to be memorized and retrieved, as 0.199N, where N means the units in the system. We also derived dynamical properties by using the statistical neurodynamics and explained the property of BAM from transient process to equilibrium state consistently.

• 一般社団法人情報処理学会の論文
• 2002-06-26

著者

• Shouno Hayaru

  Graduate School Of Human Culture Nara Women's University

• Okada Masato

  Brain Research Institute Riken

関連論文

• Classification of Idiopathic Interstitial Pneumonia on High-resolution CT Images using Counter-propagation Network
• Naive Mean Field Approximation for Image Restoration
• An Improvement of Program Partitioning Based Genetic Algorithm
• Analysis of Bidirectional Associative Memory using Self-consistent Signal to Noise Analysis and Statistical Neurodynamics(General)
• Mixed states on neural network with structural learning
• Sparsely Encoded Associative Memory Model with Forgetting Process(Regular Section)
• Dynamically Coupled Oscillators : Cooperative Behavior via Dynamical Interaction
• Naive Mean Field Approximation for Image Restoration
• Analysis of Bidirectional Associative Memory using SCSNA and Statistical Neurodynamics

スポンサーリンク