Spatial concept learning: a spiking neural network implementation in virtual and physical robots

This paper proposes an artificial spiking neural network (SNN) sustaining the cognitive 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 patterns or location on the images. Tests with novel patterns and locations were successfully completed after the acquisition learning phase. Results show that the SNN could adapts its behavior in real time when the rewarding rule changes.

Note : The following is all supplementary materials available for the article.