Modular neural architectures for robotics

作者: J. L. Buessler , J. P. Urban

DOI: 10.1007/978-3-7908-1775-1_10

关键词:

摘要: The learning of sensory-motor functions have motivated important research works that emphasize a major demand: the combination multiple neural networks to implement complex functions. A review number presents some implementations in robotics, describing purpose modular architecture, its structure, and technique was applied. second part chapter an original approach this problem network training, proposed by our group. Based on bi-directional can be trained online with simple local rules, while robotic systems interact their environment.

参考文章(69)
Lina L. E. Massone, A Biologically-Inspired Architecture for Reactive Motor Control Springer, Boston, MA. pp. 421- 438 ,(1993) , 10.1007/978-1-4615-3180-7_24
Teuvo Kohonen, Self-organized formation of topologically correct feature maps Biological Cybernetics. ,vol. 43, pp. 509- 521 ,(1988) , 10.1007/BF00337288
Suzanna Becker, Mutual information maximization: models of cortical self-organization. Network: Computation In Neural Systems. ,vol. 7, pp. 7- 31 ,(1996) , 10.1080/0954898X.1996.11978653
G. Hauska, G. Hartmann, Rolf Eckmiller, Parallel Processing in Neural Systems and Computers Parallel Processing in Neural Systems and Computers. pp. 626- 626 ,(1990)
Howard N Zelaznik, None, Advances in Motor Learning and Control ,(1996)
Klaus Schulten, Helge Ritter, Extending Kohonens Self-Organizing Mapping Algorithm to Learn Ballistic Movements Neural Computers. pp. 406- ,(1988)
Kumpati S. Narendra, Adaptive control using neural networks Neural networks for control. pp. 115- 142 ,(1990)
Roderick Murray-Smith, Tor Arne Johansen, Multiple Model Approaches to Modelling and Control Taylor & Francis. ,(1997)
Helge Ritter, Klaus Schulten, Extending Kohonen's self-organizing mapping algorithms to learn ballistic movements Proceedings of the NATO Advanced Research Workshop on Neural computers. pp. 393- 406 ,(1988) , 10.1007/978-3-642-83740-1_40