Dynamic memory by recurrent neural network and its learning by genetic algorithm

Recurrent neural networks have dynamic characteristics and can express functions of time. The recurrent neural networks can be applied to memorize robotic motions, i.e. trajectory of a manipulator. For this purpose, it is necessary to determine appropriate interconnection weights of the network. Formerly, learning algorithms based on gradient search techniques have been shown. However, it is difficult for the recurrent neural network to learn such functions while using previous approaches because of much computing requirement and limitation of memory. This paper presents a new learning scheme for the recurrent neural networks by genetic algorithm (GA). The GA is applied to determine interconnection weights of the recurrent neural networks. The GA approach is compared with the backpropagation through time which is a famous learning algorithm for the recurrent neural networks. Simulations illustrate the performance of the proposed approach.<<ETX>>

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

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

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

[4]  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.

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

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

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

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

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

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

[11]  Nostrand Reinhold,et al.  the utility of using the genetic algorithm approach on the problem of Davis, L. (1991), Handbook of Genetic Algorithms. Van Nostrand Reinhold, New York. , 1991 .

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

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

[14]  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.

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

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

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