"2"^^ . . . "Distance Measures for HyperGP with Fitness Sharing"@en . . "2"^^ . "Proceedings of the fourteenth international conference on Genetic and evolutionary computation conference companion" . . "131563" . "http://dl.acm.org/citation.cfm?id=2330241" . "RIV/68407700:21230/12:00195563!RIV13-MSM-21230___" . "RIV/68407700:21230/12:00195563" . "Distance Measures for HyperGP with Fitness Sharing" . "Philadelphia" . . . . . "artificial neural networks; fitness sharing; gp; hypergp; hyperneat; indirect encodings; tree distance measures"@en . . . "\u0160norek, Miroslav" . "Distance Measures for HyperGP with Fitness Sharing"@en . "21230" . . "2012-07-07+02:00"^^ . . "New York" . . . "[7A81F11873B7]" . . "I" . "8"^^ . "000309611100069" . "978-1-4503-1177-9" . "Distance Measures for HyperGP with Fitness Sharing" . "In this paper we propose a new algorithm called HyperGPEFS (HyperGP with Explicit Fitness Sharing). It is based on a HyperNEAT, which is a well-established evolutionary method employing indirect encoding of artificial neural networks. Indirect encoding in HyperNEAT is realized via special function called Compositional and Pattern Producing Network (CPPN), able to describe a neural network of arbitrary size. CPPNs are represented by network structures, which are evolved by means of a slightly modified version of another, well-known algorithm NEAT (NeuroEvolution of Augmenting Topologies). HyperGP is a variant of HyperNEAT, where the CPPNs are optimized by Genetic Programming (GP). Published results reported promising improvement in the speed of convergence. Our approach further extends HyperGP by using fitness sharing to promote a diversity of a population. Here, we thoroughly compare all three algorithms on six different tasks. Fitness sharing demands a definition of a tree distance measure. Among other five, we propose a generalized distance measure which, in conjunction with HyperGPEFS, significantly outperforms HyperNEAT and HyperGP on all, but one testing problems. Although this paper focuses on indirect encoding, the proposed distance measures are generally applicable." . . "ACM" . "Drchal, Jan" . "In this paper we propose a new algorithm called HyperGPEFS (HyperGP with Explicit Fitness Sharing). It is based on a HyperNEAT, which is a well-established evolutionary method employing indirect encoding of artificial neural networks. Indirect encoding in HyperNEAT is realized via special function called Compositional and Pattern Producing Network (CPPN), able to describe a neural network of arbitrary size. CPPNs are represented by network structures, which are evolved by means of a slightly modified version of another, well-known algorithm NEAT (NeuroEvolution of Augmenting Topologies). HyperGP is a variant of HyperNEAT, where the CPPNs are optimized by Genetic Programming (GP). Published results reported promising improvement in the speed of convergence. Our approach further extends HyperGP by using fitness sharing to promote a diversity of a population. Here, we thoroughly compare all three algorithms on six different tasks. Fitness sharing demands a definition of a tree distance measure. Among other five, we propose a generalized distance measure which, in conjunction with HyperGPEFS, significantly outperforms HyperNEAT and HyperGP on all, but one testing problems. Although this paper focuses on indirect encoding, the proposed distance measures are generally applicable."@en . . . . "10.1145/2330163.2330241" . . .