A Modified Recurrent Neural Network with Parametric Bias and its Application to Action Learning of a Humanoid Robot

Tani et al.'s recurrent neural network with parametric bias (RNNPB) is able to learning different time series patterns, and it has been successfully applied in action learning of robots. In this paper, we propose a novel type RNNPB using Elmann type model instead of Jordan type in the conventional model. The proposed structure makes it easy to use error back-propagation (BP) learning algorithm which has lower computational cost than back-propagation time through (BPTT) method used in Tani et al.'s model. The effectiveness of the modified RNNPB was confirmed by its application to gesture learning experiment using a humanoid robot.

[1]  Tetsuya Ogata,et al.  Extracting multi-modal dynamics of objects using RNNPB , 2005, IROS.

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  Jun Tani,et al.  Self-organization of behavioral primitives as multiple attractor dynamics: A robot experiment , 2003, IEEE Trans. Syst. Man Cybern. Part A.

[4]  Jun Tani,et al.  Self-organization of distributedly represented multiple behavior schemata in a mirror system: reviews of robot experiments using RNNPB , 2004, Neural Networks.

[5]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[6]  Shingo Mabu,et al.  Multiple Action Sequence Learning and Automatic Generation for a Humanoid Robot Using RNNPB and Reinforcement Learning , 2012 .

[7]  Michael I. Jordan.  Attractor dynamics and parallelism in a connectionist sequential machine , 1990 .

[8]  Jun Tani,et al.  Learning to generate articulated behavior through the bottom-up and the top-down interaction processes , 2003, Neural Networks.

[9]  Ronald J. Williams,et al.  A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[10]  Jeffrey L. Elman,et al.  Distributed Representations, Simple Recurrent Networks, and Grammatical Structure , 1991, Mach. Learn..

[11]  Michael I. Jordan,et al.  Forward Models: Supervised Learning with a Distal Teacher , 1992, Cogn. Sci..

[12]  Jun Tani,et al.  Generalization in Learning Multiple Temporal Patterns Using RNNPB , 2004, ICONIP.