Abstract
This paper presents a new type of neural networks, a perturbational neural network to realize incremental learning in autonomous humanoid robots. In our previous work, a virtual learning system has been provided to realize exploring plausible behavior in a robot’s brain. Neural networks can generate plausible behavior in unknown environment without time-consuming exploring. Although an autonomous robot should grow step by step, conventional neural networks forget prior learning by training with new dataset. Proposed neural networks features adding output in sub neural network to weights and thresholds in main neural network. Incremental learning and high generalization capability are realized by slightly changing a mapping of the main neural network. We showed that the proposed neural networks realize incremental learning without forgetting through numerical experiments with a two-dimensional stair-climbing bipedal robot.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hirai, K., Hirose, M., Haikawa, Y., Takenaka, T.: The development of honda humanoid robot. In: Proc. IEEE ICRA, vol. 2, pp. 1321–1326 (1998)
Mahadevan, S., Connell, J.: Automatic programming of behavior-based robots using reinforcement learning. Artificial Intelligence 55, 311–365 (1992)
Kuniyoshi, Y., Sangawa, S.: Early motor development from partially ordered neural-body dynamics: experiments with a cortico-spinal-musculo-skeletal model. Biological Cybernetics 95, 589–605 (2006)
Yamashita, I., Yokoi, H.: Control of a biped robot by using several virtual environments. In: Proceedings of the 22nd Annual Conference of the Robotics Society of Japan 1K25 (in Japanese) (2004)
Kawano, T., Yamashita, I., Yokoi, H.: Control of the bipedal robot generating the target by the simulation in virtual space (in Japanese). IEICE Technical Report 104, 65–69 (2004)
Haruno, M., Wolpert, D.M., Kawato, M.: MOSAIC model for sensorimotor learning and control. Neural Computation 13, 2201–2220 (2001)
Schaal, S., Atkeson, C.G.: Constructive incremental learning from only local information. Neural Computation 10, 2047–2084 (1998)
Yamauchi, K., Hayami, J.: Incremental learning and model selection for radial basis function network through sleep. IEICE TRANSACTIONS on Information and Systems E90-D, 722–735 (2007)
Matsuoka, K.: Sustained oscillations generated by mutually inhibiting neurons with adaptation. Biological Cybernetics 52, 367–376 (1985)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Inohira, E., Oonishi, H., Yokoi, H. (2008). Perturbational Neural Networks for Incremental Learning in Virtual Learning System. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4984. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69158-7_42
Download citation
DOI: https://doi.org/10.1007/978-3-540-69158-7_42
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69154-9
Online ISBN: 978-3-540-69158-7
eBook Packages: Computer ScienceComputer Science (R0)