000104358 001__ 104358
000104358 005__ 20190316233956.0
000104358 0247_ $$2doi$$a10.1007/s10710-006-9019-1
000104358 02470 $$2DAR$$a11320
000104358 02470 $$2ISI$$a000249551700003
000104358 037__ $$aARTICLE
000104358 245__ $$aEvolutionary morphogenesis for multi-cellular systems
000104358 269__ $$a2007
000104358 260__ $$c2007
000104358 336__ $$aJournal Articles
000104358 520__ $$aWith a gene required for each phenotypic trait, direct genetic encodings may show poor scalability to increasing phenotype length. Developmental systems may alleviate this problem by providing more efficient indirect genotype to phenotype mappings. A novel classification of multi-cellular developmental systems in evolvable hardware is introduced. It shows a category of developmental systems that up to now has rarely been explored. We argue that this category is where most of the benefits of developmental systems lie (e.g. speed, scalability, robustness, inter-cellular and environmental interactions that allow fault-tolerance or adaptivity). This article describes a very simple genetic encoding and developmental system designed for multi-cellular circuits that belongs to this category. We refer to it as the morphogenetic system. The morphogenetic system is inspired by gene expression and cellular differentiation. It focuses on low computational requirements which allows fast execution and a compact hardware implementation. The morphogenetic system shows better scalability compared to a direct genetic encoding in the evolution of structures of differentiated cells, and its dynamics provides fault-tolerance up to high fault rates. It outperforms a direct genetic encoding when evolving spiking neural networks for pattern recognition and robot navigation. The results obtained with themorphogenetic system indicate that this “minimalist” approach to developmental systems merits further study.
000104358 6531_ $$aEvolutionary Computation
000104358 6531_ $$aDevelopmental System
000104358 6531_ $$aGenotype to Phenotype Mapping
000104358 6531_ $$aEvolvable Hardware
000104358 6531_ $$aNeural Network
000104358 6531_ $$aEvolutionary Robotics
000104358 700__ $$0241581$$g103416$$aRoggen, Daniel
000104358 700__ $$aFederici, Diego
000104358 700__ $$aFloreano, Dario$$0240742$$g111729
000104358 773__ $$j8$$tGenetic Programming and Evolvable Machines$$k1$$q61-96
000104358 8564_ $$uhttps://infoscience.epfl.ch/record/104358/files/Roggen_GPEM_EvolutionaryMorphogenesis.pdf$$zn/a$$s917008
000104358 909C0 $$xU10370$$0252161$$pLIS
000104358 909CO $$ooai:infoscience.epfl.ch:104358$$qGLOBAL_SET$$pSTI$$particle
000104358 917Z8 $$x255330
000104358 937__ $$aLIS-ARTICLE-2007-003
000104358 973__ $$rNON-REVIEWED$$sPUBLISHED$$aEPFL
000104358 980__ $$aARTICLE