TY - CHAP U1 - Konferenzveröffentlichung A1 - Hagg, Alexander A1 - Mensing, Maximilian A1 - Asteroth, Alexander T1 - Evolving Parsimonious Networks by Mixing Activation Functions T2 - GECCO '17: Proceedings of the Genetic and Evolutionary Computation Conference. Berlin, Germany, July 15-19, 2017 N2 - Neuroevolution methods evolve the weights of a neural network, and in some cases the topology, but little work has been done to analyze the effect of evolving the activation functions of individual nodes on network size, an important factor when training networks with a small number of samples. In this work we extend the neuroevolution algorithm NEAT to evolve the activation function of neurons in addition to the topology and weights of the network. The size and performance of networks produced using NEAT with uniform activation in all nodes, or homogenous networks, is compared to networks which contain a mixture of activation functions, or heterogenous networks. For a number of regression and classification benchmarks it is shown that, (1) qualitatively different activation functions lead to different results in homogeneous networks, (2) the heterogeneous version of NEAT is able to select well performing activation functions, (3) the produced heterogeneous networks are significantly smaller than homogeneous networks. KW - activation function KW - heterogeneous networks KW - regression KW - bloat KW - neuroevolution SN - 978-1-4503-4920-8 SB - 978-1-4503-4920-8 U6 - https://doi.org/10.1145/3071178.3071275 DO - https://doi.org/10.1145/3071178.3071275 AX - 1703.07122 SP - 425 EP - 432 PB - Association for Computing Machinery CY - New York, NY, United States ER -