Stability of Feedback-Type Neural Networks Having Nonsymmetric Interconnections

スポンサーリンク

概要

• 論文の詳細を見る

• A Hopfield network has symmetric interconnections that carry many patterns of memory. Dynamics of the Hopfield model are explained with the energy function constructed by a quadratic form of input vectors and interconnections. However, it is difficult to implement complete symmetric interconnection with practical hardwares. Neural networks having nonsymmetric interconnections cannot be discussed using the energy function. This paper describes a method to treat stability of a Hopfield model having nonsymmetric interconnections. The discussed mathematical forms are analogous to nonequilibrium thermodynamics. A stable condition is theoretically obtained for nonsymmetrically interconnected neural networks.

• 社団法人応用物理学会の論文
• 1993-02-15

著者

• Mada Hitoshi

  School Of Science And Engineering Teikyo University

関連論文

• Transient Behavior of Voltage Holding Ratio in Nematic Liquid Crystal Cells(Optics and Quantum Electronics)
• Dielectric Properties of n-Pentyl-p-n-Cyanobiphenyl in Wide Frequency Range
• Measurement of Steady-State Current Flowing in Nematic Liquid Crystal
• A Proposal on and Verification of Surface Alignment of Liquid Crystals Aligned by Frictional Rubbing
• Pretilt Angle Dependence of Azimuthal Anchoring Energy in Nematic Liquid Crystals
• Optical Implementation of Multiple-Valued and Continuous Logics (OPTICAL COMPUTING 1)
• Stability of Feedback-Type Neural Networks Having Nonsymmetric Interconnections
• Ion Influence on Nematic Liquid Crystal Cell Impedance at Low Frequency
• Time Dependence of Impedance Characteristic of Nematic Liquid Crystal Cell
• Time Response of Liquid Crystals Aligned on Ferroelectric Layers
• Expression of Ionic Phenomena and State Equations for Nematic Liquid Crystals

もっと見る 閉じる

スポンサーリンク