Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots
Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots
复制标题
DOI：
10.1155/2019/8361369
复制
发表时间：
2019-01-01
影响因子：
--
通讯作者：
Theriault, Frederic
中科院分区：
文献类型：
--
作者：
Cyr, Andre;Theriault, Frederic
本文提出了一种人工脉冲神经网络（SNN），支持空间概念学习的认知抽象过程，嵌入虚拟和真实的机器人。基于操作性条件反射过程，机器人学习水平/垂直和左/右视觉刺激的关系，而不管它们的特定图案组成或它们在图像上的位置。在获得学习阶段之后，成功地完成了具有新图案和位置的测试。结果表明，当奖励规则发生变化时，SNN能够真实的实时自适应。
This paper proposes an artificial spiking neural network (SNN) sustaining the cognitive abstract process of spatial concept learning, embedded in virtual and real robots. Based on an operant conditioning procedure, the robots learn the relationship of horizontal/vertical and left/right visual stimuli, regardless of their specific pattern composition or their location on the images. Tests with novel patterns and locations were successfully completed after the acquisition learning phase. Results show that the SNN can adapt its behavior in real time when the rewarding rule changes.