| A MODEL FOR UNFULLY INTERCONNECTED NEURAL NETWORK |
| |
| 引用本文： | 甘强,韦钰. A MODEL FOR UNFULLY INTERCONNECTED NEURAL NETWORK[J]. 东南大学学报, 1993, 0(1) |
| |
| 作者姓名： | 甘强 韦钰 |
| |
| 作者单位： | Department of Biomedical Fngineering，Department of Biomedical Fngineering |
| |
| 摘 要： | In order to reduce the complexity of neural network connectivity,a dy-namical model for unfully interconnected neural network,including its energy func-tion,local area field and learning rule,is presented.The basic idea is to decompose aHopfield network into several subnetworks and set up some interconnections betweenthem.The statistical analysis of the associative memory process shows that the num-ber of interconnections after the first decomposition is reduced by 25% comparedwith that of the Hopfield network,but the storage capacity and the associative abilityof the network remain unchanged.With the decomposition continued,the number ofinterconnections is considerably reduced.Despite the reduction in storage capacityand associative ability with continuous decomposition,the average information capac-ity per interconnection has increased nearly by 100%.Finally the relationship be-tween high-order interconnection and multilayer network architecture is discussed.
|
A MODEL FOR UNFULLY INTERCONNECTED NEURAL NETWORK |
| |
| Gan Qiang Wei Yu. A MODEL FOR UNFULLY INTERCONNECTED NEURAL NETWORK[J]. Journal of Southeast University(English Edition), 1993, 0(1) |
| |
| Authors: | Gan Qiang Wei Yu |
| |
| Affiliation: | Department of Biomedical Engineering |
| |
| Abstract: | In order to reduce the complexity of neural network connectivity,a dy- namical model for unfully interconnected neural network,including its energy func- tion,local area field and learning rule,is presented.The basic idea is to decompose a Hopfield network into several subnetworks and set up some interconnections between them.The statistical analysis of the associative memory process shows that the num- ber of interconnections after the first decomposition is reduced by 25% compared with that of the Hopfield network,but the storage capacity and the associative ability of the network remain unchanged.With the decomposition continued,the number of interconnections is considerably reduced.Despite the reduction in storage capacity and associative ability with continuous decomposition,the average information capac- ity per interconnection has increased nearly by 100%.Finally the relationship be- tween high-order interconnection and multilayer network architecture is discussed. |
| |
| Keywords: | neural network model associative memory/unfull interconnection |
| 本文献已被 CNKI 等数据库收录！ |
|
