Developmental Learning With Behavioral Mode Tuning by Carrier-Frequency Modulation in Coherent Neural Networks

We propose a developmental learning architecture with which a motion-control system learns multiple tasks similar to each other or advanced ones incrementally and efficiently by tuning its behavioral mode. The system is based on a coherent neural network whose carrier frequency works as a mode-tuning parameter. In our experiments, we consider two tasks related to bicycle riding. The first is to ride as temporally long as the system can before it falls down (task 1). The second is an advanced one, i.e., to ride as far as possible in a certain direction (task 2). We compare developmental learning to learn task 2 after task 1 with the direct learning of task 2. We also examine the effect of the mode tuning by comparing variable-mode learning (VML), where the carrier frequency is set free to move, with fixed-mode learning (FML), where the frequency is unchanged. We find that VML developmental learning results in the most efficient learning among the possible combinations. We discuss the effects of the incremental task assignment as well as the behavioral mode tuning in developmental learning

[1]  Stephan K. Chalup,et al.  Incremental Learning in Biological and Machine Learning Systems , 2002, Int. J. Neural Syst..

[2]  廣瀬 明,et al.  Complex-valued neural networks : theories and applications , 2003 .

[3]  Nirmal K. Bose,et al.  Landmine detection and classification with complex-valued hybrid neural network using scattering parameters dataset , 2005, IEEE Transactions on Neural Networks.

[4]  D. Wolpert,et al.  Internal models in the cerebellum , 1998, Trends in Cognitive Sciences.

[5]  Kumpati S. Narendra,et al.  Adaptation and learning using multiple models, switching, and tuning , 1995 .

[6]  Takashi Omori,et al.  Emergence of symbolic behavior from brain like memory with dynamic attention , 1999, Neural Networks.

[7]  D M Wolpert,et al.  Multiple paired forward and inverse models for motor control , 1998, Neural Networks.

[8]  Akira Hirose,et al.  Coherent optical neural network that learns desirable phase values in the frequency domain by use of multiple optical-path differences. , 2003, Optics letters.

[9]  Akira Hirose,et al.  Coherent lightwave associative memory system that possesses a carrier-frequency-controlled behavior , 2003 .

[10]  Akira Hirose,et al.  Behavior control of coherent-type neural networks by carrier-frequency modulation , 1996, IEEE Trans. Neural Networks.

[11]  J. Elman.  Learning and development in neural networks: the importance of starting small , 1993, Cognition.

[12]  Minoru Asada,et al.  Environmental complexity control for vision-based learning mobile robot , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[13]  J. Elman,et al.  Rethinking Innateness: A Connectionist Perspective on Development , 1996 .

[14]  Akira Hirose,et al.  Frequency-multiplexed logic circuit based on a coherent optical neural network. , 2005, Applied optics.

[15]  Akira Hirose.  Complex-Valued Neural Networks: Theories and Applications (Series on Innovative Intelligence, 5) , 2004 .

[16]  Akira Hirose,et al.  Plastic mine detecting radar system using complex-valued self-organizing map that deals with multiple-frequency interferometric images , 2004, Neural Networks.

[17]  Douglas L. T. Rohde,et al.  Language acquisition in the absence of explicit negative evidence: how important is starting small? , 1999, Cognition.

[18]  Shuji Hashimoto,et al.  Temperature Switching in Neural Network Ensemble , 2000 .

[19]  R. Llinás,et al.  Coherent 40-Hz oscillation characterizes dream state in humans. , 1993, Proceedings of the National Academy of Sciences of the United States of America.

[20]  Minoru Asada,et al.  Purposive Behavior Acquisition for a Real Robot by Vision-Based Reinforcement Learning , 2005, Machine Learning.

[21]  Danielle M. Santarelli.  The developing brain. , 1969, Nature.

[22]  Minoru Asada,et al.  Cognitive developmental robotics as a new paradigm for the design of humanoid robots , 2001, Robotics Auton. Syst..

[23]  Akira Hirose,et al.  Complex-Valued Neural Networks: Theories and Applications , 2003 .

[24]  A Hirose,et al.  Coherent optical neural networks that have optical-frequency-controlled behavior and generalization ability in the frequency domain. , 1996, Applied optics.

[25]  Juyang Weng,et al.  Auditory learning: a developmental method , 2005, IEEE Transactions on Neural Networks.