Learning multiple goal-directed actions through self-organization of a dynamic neural network model: A humanoid robot experiment
Learning multiple goal-directed actions through self-organization of a dynamic neural network model: A humanoid robot experiment
复制标题
DOI：
10.1177/1059712308089185
复制
发表时间：
2008-01-01
影响因子：
1.6
通讯作者：
Tani, Jun
中科院分区：
文献类型：
--
作者：
Nishimoto, Ryunosuke;Namikawa, Jun;Tani, Jun
我们介绍了一个模型，占认知机制的学习和产生多个目标导向的行动。该模型采用了所谓的“感觉向前模型”的新思想，该模型被认为在人类和猴子的下顶叶皮层中起作用，以产生熟练的行为。一组不同的目标导向的动作可以由感官前向模型通过利用其所获得的前向动态的初始灵敏度特性来生成。对我们机器人实验的分析定性地显示了学习中的泛化如何针对情境变化实现，以及自上而下的对特定目标状态的意图如何与来自现实的自下而上的感觉相协调。
We introduce a model that accounts for cognitive mechanisms of learning and generating multiple goal-directed actions. The model employs the novel idea of the so-called "sensory forward model," which is assumed to function in inferior parietal cortex for the generation of skilled behaviors in humans and monkeys. A set of different goal-directed actions can be generated by the sensory forward model by utilizing the initial sensitivity characteristics of its acquired forward dynamics. The analyses on our robotics experiments show qualitatively how generalization in learning can be achieved for situational variances, and how the top-down intention toward a specific goal state can reconcile with the bottom-up sensation from reality.