000087949 001__ 87949
000087949 005__ 20190812204945.0
000087949 02470 $$2ISI$$a000241446400068
000087949 02470 $$2DAR$$a9537
000087949 037__ $$aCONF
000087949 245__ $$aNeuroevolution with Analog Genetic Encoding
000087949 269__ $$a2006
000087949 260__ $$c2006
000087949 336__ $$aConference Papers
000087949 490__ $$aLecture Notes in Computer Science$$v4193
000087949 520__ $$aThe evolution of artificial neural networks (ANNs) is often used to tackle difficult control problems. There are different approaches to the encoding of neural networks in artificial genomes. Analog Genetic Encoding (AGE) is a new implicit method derived from the observation of biological genetic regulatory networks. This paper shows how AGE can be used to simultaneously evolve the topology and the weights of ANNs for complex control systems. AGE is applied to a standard benchmark problem and we show that its performance is equivalent or superior to some of the most powerful algorithms for neuroevolution in the literature.
000087949 6531_ $$aNeuroevolution
000087949 6531_ $$aNeural Networks
000087949 6531_ $$aAnalog Genetic Encoding
000087949 6531_ $$aCTRNN
000087949 6531_ $$aAGE
000087949 6531_ $$aImplicit Encoding
000087949 6531_ $$aImplicit Genetic Encoding
000087949 6531_ $$aEvolutionary Robotics
000087949 700__ $$0243223$$g167254$$aDürr, Peter
000087949 700__ $$0241582$$g140974$$aMattiussi, Claudio
000087949 700__ $$aFloreano, Dario$$g111729$$0240742
000087949 7112_ $$d9-13 September 2006$$cReykjavik, Iceland$$aParallel Problem Solving from Nature - PPSN iX
000087949 773__ $$j9$$tProceedings of the 9th Conference on Parallel Problem Solving from Nature (PPSN iX)$$q671--680
000087949 8564_ $$zURL$$uhttp://ppsn2006.raunvis.hi.is/
000087949 8564_ $$zn/a$$uhttps://infoscience.epfl.ch/record/87949/files/DuerrMattiussiFloreano2006_PPSNIX_NeuroAGE.pdf$$s679733
000087949 909C0 $$xU10370$$pLIS$$0252161
000087949 909CO $$ooai:infoscience.tind.io:87949$$qGLOBAL_SET$$pconf$$pSTI
000087949 917Z8 $$x255330
000087949 937__ $$aLIS-CONF-2006-013
000087949 973__ $$rREVIEWED$$sPUBLISHED$$aEPFL
000087949 980__ $$aCONF