RT Journal Article ID 0131cc735141927f A1 Rudenko, Oleg G. A1 Bezsonov , Alexander A. T1 Coevolving Feedforward Neural Networks JF Journal of Automation and Information Sciences JO JAI(S) YR 2016 FD 2016-12-21 VO 48 IS 9 SP 36 OP 48 K1 feedforward neural networks K1 coevolving K1 evolutionary algorithm K1 cooperation and competition models K1 populations totality K1 networks synthesis AB An evolutionary algorithm of determining the architecture of feedforward neural networks and their training is proposed, based on the coevolutionary models of cooperation and competition with using of clustering algorithms for partitioning the main problem of neural network synthesis into subtasks which are to be solved in certain sub-populations. The proposed algorithm implements an environment that is conducive to cooperation and competition of populations in which every individual is a feedforward neural network, and the totality of the populations is responsible for the final solution of the set problem. The simulation results confirm the effectiveness of the proposed method of feedforward neural networks synthesis. PB Begell House LK https://www.dl.begellhouse.com/journals/2b6239406278e43e,25e27c3f78c6e23d,0131cc735141927f.html