Performance of Associative Memory Using Partially-connected Networks

摘要：

From both a neurobiological viewpoint and animplementation perspective,the neuron network ispartially-connected.In this paper,we show thatassociative memory networks with complex topology.Owing to the partial connection in delta distributenetwork,the associative memory has feature of higherstorage capacity,but the basin of attraction is shrunk.The comparison of the performance among the ERnetwork,Small-world network and delta distributenetwork investigates that associative,memorynetworks performance does not simply depend on themean degree of the neurons,but also on the structureof the connectivity.The simulation shows that the deltadistribute network performance the most efficientperformance.

关键词： associative memory partially-connected storage capacity basin of attraction

作者: Min Xia Yang Tang Jianan Fang

作者单位: College of Information Science and Technology,Donghua University,Shanghai China,201620

会议类型: 国际会议

会议名称: 2008 3rd International Conference on Intelligent System and Knowledge Engineering(第三届智能系统与知识工程国际会议)(ISKE 2008)

会议地点: 厦门

会议语种:英文

页码: 867-872

在线出版日期: 2008-11-17（万方平台首次上网日期，不代表论文的发表时间）