Evolved Patterns of Connectivity in Associative Memory Models

摘要：

This paper investigates possible connection strategies in sparsely connected associative memory models. This is interesting because real neural networks must have both efficient performance and minimal wiring length. We show, by using a Genetic Algorithm to evolve networks, that connection strategies, like those with exponentially reducing numbers of connections from near to far units, work efficiently and have low wiring costs. This implies, when modelling brain-like abilities in artificial neural networks, that it is possible to get good performance even with minimal numbers of long range connections.

关键词： Associative Memory Neural Network Genetic Algorithm Small-World Network Connectivity.

作者: Rod Adams Lee Calcraft Neil Davey

作者单位: Science and Technology Research Institute University of Hertfordshire, UK

会议类型: 国际会议

会议名称: Firth IEEE International Conference on Cognitive Informatics(第五届认知信息国际会议)

会议地点: 北京

会议语种:英文

页码: 754-759

在线出版日期: 2006-07-17（万方平台首次上网日期，不代表论文的发表时间）