A novel spatial architecture artificial neural network based on multilayer feedforward network with mutual inhibition among hidden units - Details

Author：

Yang, Gang (Yang, Gang.) | Qiao, Junfei (Qiao, Junfei.) (Scholars：乔俊飞) | Yuan, Mingzhe (Yuan, Mingzhe.)

Indexed by：

EI Scopus

Abstract：

We　propose　a　Spatial　Artificial　Neural　Network　(SANN)　with　spatial　architecture　which　consists　of　a　multilayer　feedforward　neural　network　with　hidden　units　adopt　recurrent　lateral　inhibition　connection,　all　input　and　hidden　neurons　have　synapses　connections　with　the　output　neurons.　In　addition,　a　supervised　learning　algorithm　based　on　error　back　propagation　is　developed.　The　proposed　network　has　shown　a　superior　generalization　capability　in　simulations　with　pattern　recognition　and　non-linear　function　approximation　problems.　And,　the　experimental　also　shown　that　SANN　has　the　capability　of　avoiding　local　minima　problem.　©　2011　Springer-Verlag.

Keyword：

Functions Recurrent neural networks Pattern recognition Backpropagation algorithms Network architecture Multilayers Feedforward neural networks Multilayer neural networks

Author Community：

[ 1 ] [Yang, Gang]Intelligent Systems Institute, College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China
[ 2 ] [Qiao, Junfei]Intelligent Systems Institute, College of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China
[ 3 ] [Yuan, Mingzhe]Shenyang Institute of Automation, Chinese Academy of Science, Shenyang 110016, China