Research on design method of small world property ESN - Details

Author：

Bo, Yingchun (Bo, Yingchun.) | Qiao, Junfei (Qiao, Junfei.) (Scholars：乔俊飞) | Wang, Shuwei (Wang, Shuwei.)

Indexed by：

EI Scopus

Abstract：

Aim　to　solve　the　problems　of　structure　design　and　parameters　selection　about　conventional　ESN,　a　small　world　property　ESN　(SWESN)　is　proposed　in　this　paper.　Neuron　space　growth　algorithm　is　adopted　to　generate　a　physical　network　with　small　world　topology　on　2-D　plane　firstly,　and　then　the　nodes　and　the　connections　of　the　physical　network　are　mapped　into　the　neurons　in　reservoir　of　SWESN,　Thus　the　dynamic　neuron　reservoir　(DNR)　in　SWESN　has　small　world　characteristic.　In　addition,　different　typical　neurons　are　adopted　in　the　reservoir.　The　simulation　experiments　confirms　that　the　SWESN　generated　by　this　method　could　create　more　abundant　dynamic　behavior　than　conventional　ESN,　and　SWESN　exceeds　conventional　ESN　both　at　robustness　and　at　anti-disturbance　ability.　©　2011　Springer-Verlag.

Keyword：

Dynamics Neurons Robustness (control systems) Neural networks

Author Community：

[ 1 ] [Bo, Yingchun]College of Electronic and Control Engineering, Beijing University of Technology, Beijing 100124, China
[ 2 ] [Qiao, Junfei]College of Electronic and Control Engineering, Beijing University of Technology, Beijing 100124, China
[ 3 ] [Wang, Shuwei]College of Architecture and Civil Engineering, Beijing University of Technology, Beijing 100124, China