Heuristic learning by genetic algorithm for recurrent neural network

Recurrent neural networks have dynamic characteristics and express functions of time. Recurrent neural networks can memorize robotic motions, i.e., trajectories of manipulators For this purpose, it is necessary to determine appropriate interconnection weights of the network. A new learning scheme for the recurrent neural networks by genetic algorithm (GA) is presented. The GA is applied to determine interconnection weights of the recurrent neural networks. The proposed approach is compared with backpropagation through time for recurrent neural networks. Simulation illustrates the performance of the proposed approach