Format

Send to

Choose Destination
Neural Netw. 2004 Oct-Nov;17(8-9):1273-89.

Self-organization of distributedly represented multiple behavior schemata in a mirror system: reviews of robot experiments using RNNPB.

Author information

1
Brain Science Institute, RIKEN, 2-1 Hirosawa, Wako-shi, Saitama 351-0198, Japan. tani@brain.riken.go.jp

Erratum in

  • Neural Netw. 2005 Jan;18(1):103-4.

Abstract

The current paper reviews a connectionist model, the recurrent neural network with parametric biases (RNNPB), in which multiple behavior schemata can be learned by the network in a distributed manner. The parametric biases in the network play an essential role in both generating and recognizing behavior patterns. They act as a mirror system by means of self-organizing adequate memory structures. Three different robot experiments are reviewed: robot and user interactions; learning and generating different types of dynamic patterns; and linguistic-behavior binding. The hallmark of this study is explaining how self-organizing internal structures can contribute to generalization in learning, and diversity in behavior generation, in the proposed distributed representation scheme.

PMID:
15555866
DOI:
10.1016/j.neunet.2004.05.007
[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Elsevier Science
Loading ...
Support Center