Self-Organization of Behavior Primitives as Multiple Attractor Dynamics by the "Forwarding Forward Model" network

スポンサーリンク

概要

• 論文の詳細を見る

• In this paper, we investigated how behavior primitives are self-organized in our previously proposed the "forwarding forward model" neural network model in the context of robot imitation learning. The model is characterized with the so-called parametric biases which adaptively modulate for embedding different behavior patterns in a single recurrent neural net in a distributed way. Our experiments, using a real robot, showed that a set of end-point and oscillatory behavior patterns are learned as fixed points and limit cycle dynamics respectively with adapting parametric bias for each. Our further analysis showed that diverse behavior patterns other than learned patterns were also generated because of self-organization of nonlinear map between spaces of the parametric biases and that of behaviors. It is discussed that such diversity emerges because primitives are represented distributedly in the network.

• 社団法人電子情報通信学会の論文
• 2002-01-21

著者

• Tani Jun

  The Brain Science Institute Riken

関連論文

• Learning to generate articulated behavior by the "forwarding forward model" network
• Self-Organization of Behavior Primitives as Multiple Attractor Dynamics by the "Forwarding Forward Model" network

スポンサーリンク