Mode-Utilizing Developmental Learning Based on Coherent Neural Networks
We propose a mode-utilizing developmental learning method. Thereby a system possesses a mode parameter and learns similar or advanced tasks incrementally by using its cumulative skill. We construct the system based on the coherent neural network where we choose its carrier frequency as the mode parameter. In this demonstration, we assume two tasks: basic and advanced. The first is to ride a bicycle as long as the system can before it falls. The second is to ride as far as possible. It is demonstrated that the system finds self-organizingly a suitable value of the mode parameter in the second task learning. The learning is performed efficiently to succeed in riding for a long distance.
KeywordsCarrier Frequency Mode Parameter Rolling Angle Hill Climbing Neural Network Ensemble
Unable to display preview. Download preview PDF.
- 2.Omori, T., Mochizuki, A.: PATON: A model of context dependent memory access with an attention mechanism. In: Brain Processes, Theories and Models, pp. 134–143. MIT Press, Cambridge (1995)Google Scholar
- 4.Hartono, P., Hashimoto, S.: Temperature switching in neural network ensemble. J. Signal Processing 4, 395–402 (2000)Google Scholar
- 6.Hirose, A., Tabata, C., Ishimaru, D.: Coherent neural network architecture realizing a self-organizing activeness mechanism. In: Proc. of Int’l Conf. on Knowledge-based Eng. Sys. KES 2001, Osaka, September 6-8, 2001, pp. 576–580 (2001)Google Scholar
- 7.Hirose, A., Ishimaru, D.: Context-dependent behavior of coherent neural systems based on self-organizing mapping of carrier frequency values. In: Proc. of Int’l Conf. on Knowledge-based Engineering Systems KES 2002, Crema, September 16-18, 2002, pp. 638–642 (2002)Google Scholar
- 8.Kawata, S., Hirose, A.: Coherent lightwave neural network systems. In: Hirose, A. (ed.) Complex- Valued Neural Networks: Theories and Appliactions. The Series on Innovative Intelligence, World Scientific Publishing Co., Singapore (2003)Google Scholar