A memristor property of an amorphous Sn–Ga–O (α-TGO) thin-film device deposited using a mist chemical-vapor-deposition (mist-CVD) method has been found. The α-TGO device can be manufactured at a low cost because it does not include rare metals such as In. Moreover, it is expected that the α-TGO device can be manufactured at an even lower cost because the mist-CVD method is performed at atmospheric pressure. Here, the α-TGO layer was deposited using a hot-wall-type mist-CVD method. The hysteresis curve of the memristor characteristic was certainly obtained, and the electric resistances for the high- and low-resistance states were stably repeated at least 20 times. Although the switching ratio and repeatability are not sufficient in the case that it is applied to resistive random access memories, they are acceptable for some applications such as synapse elements in neuromorphic systems.

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.