Influence of characteristic variation of oxide semiconductor and comparison of the activation function in neuromorphic hardware

Abstract

As the amount of data that people handle increases, the conventional Neumann-type computer architecture is reaching its limits. Therefore, research on hardware implementation of machine learning systems is being actively conducted. In this paper, we have implemented and evaluated neuromorphic hardware that realizes human brain neurons and synapses using oxide semiconductor of amorphous In-Ga-Zn-O (a-IGZO) and a cellular neural network. It was confirmed how variations of initial resistance and deterioration rate of the oxide semiconductor affect operation accuracy of the neuromorphic hardware. Furthermore, we clarified that an activation function suitable for the hardware implementation is a ReLU function.