全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...
物理学报  2007 

Associative memory and segmentation in the neural system under stimulation of stochastic or chaotic perceptual singals
神经系统中随机和混沌感知信号的联想记忆与分割

Keywords: neural network,spatiotemporal pattern,associative memory,stochastic resonance
神经网络
,空时模式,联想记忆,随机共振

Full-Text   Cite this paper   Add to My Lib

Abstract:

We present in this paper some results on the temporal segmentation and retrieval of stored memories or patterns using neural networks composed of spiking neurons.Respecting the working environment,we present the network with stochastic or chaotic stimuli as their extremely working conditions and also with noise.We attempt to give an explanation to the function of memory retrieval of the brain system,where the stimuli usually may not be constant,sinusoidal or periodic,but rather chaotic or stochastic.For an input pattern which is a superposition of several stored patterns,it is shown that the proposed neuronal network model is capable of segmenting out each pattern one after another as synchronous firings of a subgroup of neurons,and if a corrupted input pattern is presented,the network is shown to be able to retrieve the perfect one,that is it has the function of associative memory.By thorougly adjusting the parameters,such as the coupling strength and the intensity of the noise,the temporal segmentation attains its optimal performance at intermediate noise intensity,which reminds of the stochastic resonance observed in the coupled spiking neuronal networks.

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133