Self-organization of distributedly represented multiple behavior schemata in a mirror system: reviews of robot experiments using RNNPB
Self-organization of distributedly represented multiple behavior schemata in a mirror system: reviews of robot experiments using RNNPB
复制标题
DOI：
10.1016/j.neunet.2004.05.007
复制
发表时间：
2004-10
期刊：
影响因子：
--
通讯作者：
J. Tani;Masato Ito;Y. Sugita
中科院分区：
文献类型：
--
作者：
J. Tani;Masato Ito;Y. Sugita
本文综述了一种连接主义模型，即带有参数偏差的递归神经网络（RNNPB），该模型可以通过网络以分布式的方式学习多个行为模式。网络中的参数偏差在行为模式的产生和识别中都起着至关重要的作用。它们通过自我组织足够的记忆结构充当镜像系统。综述了三种不同的机器人实验：机器人与用户交互；学习和生成不同类型的动态模式；以及语言和行为的结合。本研究的特点是解释在提出的分布式表示方案中，自组织内部结构如何有助于学习的泛化和行为生成的多样性。
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.