E·voiution of Topology and Wei,ght-s. of Neural Netwo·rks. Using.Semi Genetic Operators
1. A. Yous-if · DOAJ (DOAJ: Directory of Open Access Journals) · 2017
Evolutionary·co.nipimit'iQo is a· c'!a s of glbbal ·searb techniq based on the lei.lffi:ing process ,of g po_pl)'latiog-·of pote.n:tiaf solutions to a ven probl_e-ID'. thahas .been succe_ssfull'y applied 19 v ety of prQblern, lll thls paper a riew approach to. design lie_ ural ne'twQj:ks based oh ev.ohltipnary -computa.tio.rt i·s pre.Seri-L _A tine-f.!£ clurP.mosome 'repr:esentati:on or the etwor}< i_s. u_secl: 'Q.y genetiC gperntb_l:s, whicQ allow th¢ voJution of.the chitecture and' weight-s ·simMltaneousfy without the ne¢d : tlocal ·-v.:e!gh_t-s· opthnization. Dii$ , paper - d- cribes .t he approach, the" o.per HQ(S and rep 'H:tS r \llt$ '()[the a}Jplicati:on :Qf this te6hnique-.to- ;;everal biAal)l cl'iissifi·cation prob eros