Neuron network training system for Robot responding intelligently to input light stimuli
Baoping Xiao, Xu Chang, Lijun Xu, Qinhua Luo · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 2007
This article consists of an elementary eight neuron network that uses Hebbian Learning to train a robot to respond intelligently to input light stimuli. In order to reach our end goal, a three-neuron neural networks in C and thoroughly testing it with LEDs and hyperterm are programmed firstly. Then extend this to a four-neuron network and finally to an eight-neuron network, with thorough testing at each level of complexity. The hardware interface is added. This involved integration of stepper motor control code into our neural network such that the stepper motors would step when the 'motor' neurons fired.