Neuroevolution: Problems, algorithms, and experiments

The article describes the problematic issues of neuroevolution, i.e. a promising approach for solving complex problems of machine learning, neural networks, adaptive management and multi-agent systems, evolutionary robotics, gaming strategies, and computer art. The authors have suggested neuro evolutional algorithm and presented experiment results on a standard task: the balancing trolley with two flagpoles of different lengths.

[1]  Frédéric Gruau,et al.  Genetic synthesis of Boolean neural networks with a cell rewriting developmental process , 1992, [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks.

[2]  Sergey Rodzin,et al.  Theory of bionic optimization and its application to evolutionary synthesis of digital devices , 2014, Proceedings of IEEE East-West Design & Test Symposium (EWDTS 2014).

[3]  Thomas Jansen,et al.  Theory of Evolutionary Computation , 2011, Algorithmica.

[4]  Risto Miikkulainen,et al.  Solving Non-Markovian Control Tasks with Neuro-Evolution , 1999, IJCAI.

[5]  Shinichi Honiden,et al.  CMA-TWEANN: efficient optimization of neural networks via self-adaptation and seamless augmentation , 2012, GECCO '12.

[6]  Risto Miikkulainen,et al.  Evolving Neural Networks through Augmenting Topologies , 2002, Evolutionary Computation.