赤外線通信を用いたSpiking Neural NetworkによるXOR学習 <Abstract> Spiking Neural Network(SNN), which communicates among neurons by spikes, can perform information processing with low power consumption. By adding the spiking neuron function to the sensor node of the sensor network, the sensor network can obtain an ability of distributed information processing like the brain. This paper presents a SNN with infrared communications as the first step of for realizing the above concept. Neurons are implemented by field programmable gate array, which are linked by IR communications. The implemented SNN succeeded in acquiring the XOR function through reinforcement learning. |