A Fuzzy-Like Phenomenon in a Dynamic Neural Network (Neural Networks and Bioengineering)
スポンサーリンク
概要
- 論文の詳細を見る
A fuzzy-like phenomenon in a dynamic neural network is demonstrated and analyzed. The network operates as a dynamic associative memory. Each neuron of the dynamic neural network has an all-or-none output and exponentially decaying refractoriness. When several related patterns are stored in the dynamic neural network and an external stimulus with a property shared by two of the stored patterns is applied to the neural network, the output of the neural network dynamically transits between the two stored patterns. The frequency ratio that the network visits the two stored patterns is dependent on the ratio of the Hamming distances between the external pattern and the two stored patterns. This phenomenon is similar to the human decision-making process, some of which characteristics can be described by fuzzy set theory. A framework for the analysis of this phenomenon is proposed, and is used to derive sufficient conditions which ensure the dynamical transition between the two stored patterns. The properties of the transition in the network are also discussed.
- 社団法人電子情報通信学会の論文
- 2003-08-01
著者
-
Aihara Kazuyuki
Department Of Complex Science And Engineering Graduate School Of Frontier Science University Of Toky
-
Aihara Kazuyuki
Department Of Mathematical Engineering And Information Physics Graduate School Of Engineering The Un
-
WANG Zhijie
Department of Mathematical Engineering and Information Physics, Graduate School of Engineering, the
-
Wang Zhijie
Department Of Mathematical Engineering And Information Physics Graduate School Of Engineering The Un
-
Wang Zhijie
Department of Electrical Engineering, Dong Hua University, Shanghai, 200051, People's Republic of China
関連論文
- Back-Propagation Learning of Infinite-Dimensional Dynamical Systems
- Solving large scale traveling salesman problems by chaotic neuodynamics
- The Change of Memory Formation According to STDP in a Continuous-Time Neural Network Model
- Noise-Enhanced Neuronal Coding of Chaotic Dynamics
- Global Bifurcation Structure of Chaotic Neural Networks and its Application to Optimization Problems
- False Nearest Neighbor Analysis of Japanese Vowels
- Chaotic Simulated Annealing by a Neural Network Model with Transient Chaos
- Chaos in Neural Networks Composed of Coincidence Detector Neurons
- Back-Propagation Learning of Infinite-Dimensional Dynamical Systems
- Back-Propagation Learning of Infinite-Dimensional Dynamical Systems
- Dynamical Neural Network Model for Hippocampal Memory (Special Section on Nonlinear Theory and Its Applications)
- Naming the Neuron in Vain
- Nonlinear Roll Motion of a Flooded Ship in Regular Waves
- A Fuzzy-Like Phenomenon in Chaotic Autoassociative Memory
- A Fuzzy-Like Phenomenon in a Dynamic Neural Network (Neural Networks and Bioengineering)
- Associative dynamics of color images in a large-scale chaotic neural network
- Hierarchical Structure among Invariant Subspaces of Chaotic Neural Networks
- A Spatially-Ordered Pacemaker Observed in Squid Giant Axons
- Local Density of Electronic States in MgB2 Studied by Scanning Tunneling Microscopy
- A Phenomenon Like Stochastic Resonance in the Process of Spike-Timing Dependent Synaptic Plasticity
- Dynamical inter-region coupling in the brain: A meso-scopic model from a dynamical systems viewpoint