Chaotic Image Retrieval in Markovian Asymmetric Neural Networks with Sign-Constrained Synaptic Couplings

スポンサーリンク

概要

• 論文の詳細を見る

• We propose a simple asymrnetric neural network which exhibits chaotic motions inretrieval dynamics with a finite number of memory patterns. The characteristicfeature of the model is that 1.he synaptic couplings are designed in such a way thateach neuron is given an exclusively excitatory or inhibitory function, i.e., aphysiological constraint of the Date hypothesis is taken into account. The updatingrule of the neurons is assumed to be simple Markovian stochastic dynamics of the Lit-tie type (without time delay) in which the threshold for neurott firing is incorporated.Our analysis is based on the exact time evolution equatiozas derived in the ther-modynamic limit for the macroscopic pattern overlaps. Itis shown that chaotic imageretrieval can take place only when a finite amount of stochastic noise exists.asymmetric neural network, chaotic image retrieval, Little dynamics, nonlinearmaster equation, sign-constrained synaptic couplings

• 社団法人日本物理学会の論文
• 1990-05-15

著者

• Shiino Masatoshi

  Department of Applied Physics

• Fukai T

  Kobe Univ. Kobe

• Fukai Tomoki

  Department Of Electronics Tokai University

• Shiino M

  Saitama Univ. Saitama

関連論文

• Nonlinear Master Equation Approach to Asymmertrica Neural Networks of the Hopfield-Hemmen Type
• Stochastic Quantization Method of Fermion Fields
• Stochastic Quantization of Linearized Euclidean Gravity and No-Ghost Feynman Rules : Particles and Fields
• Associative Memory of Analog Networks without the Energy Concept Using Biased Patterns and Positive-Valued Transfer Functions
• Self-organized two-state membrane potential transitions in a network of realistically modeled cortical neurons
• A possible functional organization of the corticostriatal input within the weakly-correlated striatal activity : a modeling study
• Chaotic Image Retrieval in Markovian Asymmetric Neural Networks with Sign-Constrained Synaptic Couplings
• Statistical mechanics of attractor neural networks and self-consistent signal-to-noise analysis : analog neural networks with nonmonotonic transfer functions and enhancement of the storage capacity(New Developments in Statistical Physics Similarities in D
• Critical Behaviour of Spin Relaxation in EuS
• H-Theorem with Generalized Relative Entropies and the Tsallis Statistics

スポンサーリンク