000148243 001__ 148243
000148243 005__ 20190316234746.0
000148243 0247_ $$2doi$$a10.1109/MCI.2010.937319
000148243 022__ $$a1556-603X
000148243 02470 $$2ISI$$a000282406000002
000148243 037__ $$aARTICLE
000148243 245__ $$aGenetic representation and evolvability of modular neural controllers
000148243 269__ $$a2010
000148243 260__ $$bInstitute of Electrical and Electronics Engineers$$c2010
000148243 336__ $$aJournal Articles
000148243 520__ $$aThe manual design of con- trol systems for robotic devices can be challenging. Methods for the automatic synthesis of control systems, such as the evolution of artificial neural networks, are thus widely used in the robotics community. However, in many robotic tasks where multiple interdependent control problems have to be solved simultaneously, the performance of conventional neuroevolution techniques declines. In this paper, we identify interference between the adaptation of different parts of the control system as one of the key challenges in the evolutionary synthesis of artificial neural networks.As modular net- work architectures have been shown to reduce the effects of such interference, we propose a novel, implicit modular genetic representation that allows the evolutionary algorithm to automatically shape modular network topologies. Our experiments with plastic neural networks in a simple maze learning task indicate that adding a modular genetic representation to a state-of-the-art implicit neuroevolution method leads to better algorithm performance and increases the robustness of evolved solutions against detrimental mutations.
000148243 6531_ $$aCooperative Coevolution
000148243 6531_ $$aEvolution
000148243 6531_ $$aNetworks
000148243 6531_ $$aClassification
000148243 6531_ $$aRobot
000148243 6531_ $$aEvolutionary Robotics
000148243 700__ $$0243223$$aDürr, Peter$$g167254
000148243 700__ $$0241582$$aMattiussi, Claudio$$g140974
000148243 700__ $$0240742$$aFloreano, Dario$$g111729
000148243 773__ $$j5$$k3$$q10-19$$tIEEE Computational Intelligence Magazine
000148243 8564_ $$s987479$$uhttps://infoscience.epfl.ch/record/148243/files/D%C3%BCrr%2CP.%2CMattiussi%2CC.andFloreano%2CD.%282010%29Geneticrepresentationandevolvabilityofmodularneuralcontrollers.pdf$$yPublisher's version$$zPublisher's version
000148243 909C0 $$0252161$$pLIS$$xU10370
000148243 909CO $$ooai:infoscience.tind.io:148243$$pSTI$$particle$$qGLOBAL_SET
000148243 917Z8 $$x111729
000148243 917Z8 $$x111729
000148243 917Z8 $$x111729
000148243 917Z8 $$x255330
000148243 937__ $$aEPFL-ARTICLE-148243
000148243 973__ $$aEPFL$$rREVIEWED$$sPUBLISHED
000148243 980__ $$aARTICLE