Neuroevolution: from architectures to learning Export

@article{citeulike:2343726, abstract = {Abstract Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern classification to robot control. In order to design a neural network for a particular task, the choice of an architecture (including the choice of a neuron model), and the choice of a learning algorithm have to be addressed. Evolutionary search methods can provide an automatic solution to these problems. New insights in both neuroscience and evolutionary biology have led to the development of increasingly powerful neuroevolution techniques over the last decade. This paper gives an overview of the most prominent methods for evolving ANNs with a special focus on recent advances in the synthesis of learning architectures.}, author = {Floreano, Dario and D\"{u}rr, Peter and Mattiussi, Claudio}, booktitle = {Evolutionary Intelligence}, citeulike-article-id = {2343726}, citeulike-linkout-0 = {http://dx.doi.org/10.1007/s12065-007-0002-4}, day = {21}, doi = {10.1007/s12065-007-0002-4}, journal = {Evolutionary Intelligence}, keywords = {07, 5s, genotype-encoding, neural-network, neuroevolution, nn, survey}, month = {January}, pages = {47--62}, posted-at = {2008-02-06 23:14:16}, priority = {5}, publisher = {Springer}, title = {Neuroevolution: from architectures to learning}, url = {http://dx.doi.org/10.1007/s12065-007-0002-4}, volume = {1}, year = {2008} }

TY - JOUR ID - citeulike:2343726 L3 - citeulike-article-id:2343726 N2 - Abstract Artificial neural networks (ANNs) are applied to many real-world problems, ranging from pattern classification to robot control. In order to design a neural network for a particular task, the choice of an architecture (including the choice of a neuron model), and the choice of a learning algorithm have to be addressed. Evolutionary search methods can provide an automatic solution to these problems. New insights in both neuroscience and evolutionary biology have led to the development of increasingly powerful neuroevolution techniques over the last decade. This paper gives an overview of the most prominent methods for evolving ANNs with a special focus on recent advances in the synthesis of learning architectures. JF - Evolutionary Intelligence EP - 62 TI - Neuroevolution: from architectures to learning PB - Springer VL - 1 T2 - Evolutionary Intelligence SP - 47 KW - 07 KW - 5s KW - genotype-encoding KW - neural-network KW - neuroevolution KW - nn KW - survey AU - Floreano, Dario AU - Dürr, Peter AU - Mattiussi, Claudio PY - 2008/01/21/ UR - http://dx.doi.org/10.1007/s12065-007-0002-4 ER -