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.<<ETX>>

[1]  Barak A. Pearlmutter.  Learning State Space Trajectories in Recurrent Neural Networks , 1989, Neural Computation.

[2]  Jan Torreele,et al.  Temporal Processing with Recurrent Networks: An Evolutionary Approach , 1991, ICGA.

[3]  H. de Garis.  Genetic programming: building nanobrains with genetically programmed neural network modules , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[4]  Toshio Fukuda,et al.  Coordinative behavior in evolutionary multi-agent system by genetic algorithm , 1993, IEEE International Conference on Neural Networks.

[5]  Yoshiki Uchikawa,et al.  Learning process of recurrent neural networks , 1991, [Proceedings] 1991 IEEE International Joint Conference on Neural Networks.

[6]  M. Gherrity,et al.  A learning algorithm for analog, fully recurrent neural networks , 1989, International 1989 Joint Conference on Neural Networks.

[7]  Toshio Fukuda,et al.  Theory and applications of neural networks for industrial control systems , 1992, IEEE Trans. Ind. Electron..

[8]  D. E. Goldberg,et al.  Genetic Algorithms in Search , 1989 .

[9]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[10]  Kenji Doya,et al.  Adaptive neural oscillator using continuous-time back-propagation learning , 1989, Neural Networks.

[11]  L. Darrell Whitley,et al.  Genetic algorithms and neural networks: optimizing connections and connectivity , 1990, Parallel Comput..

[12]  Toshio Fukuda,et al.  Neuromorphic control: adaptation and learning , 1992, IEEE Trans. Ind. Electron..

[13]  Kazuhiro Kosuge,et al.  Selfish and coordinative planning for multiple mobile robots by genetic algorithm , 1992, [1992] Proceedings of the 31st IEEE Conference on Decision and Control.

[14]  Andrew H. Fagg,et al.  Genetic programming approach to the construction of a neural network for control of a walking robot , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[15]  Toshio Fukuda,et al.  Hierarchical intelligent control for robotic motion , 1994, IEEE Trans. Neural Networks.

[16]  Paul J. Werbos,et al.  Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.