Artificial neural networks using poly-Si thin-film transistors

Abstract

We are developing neural networks using thin-film transistors (TFTs). By adopting an interconnect-type neural network and utilizing a characteristic degradation of poly-Si TFTs as a variable strength of synapse connection, which was originally an issue, we realized the neuron consisting of eight TFTs and synapse of only one TFT. Particularly in this presentation, we confirmed that the learning efficiency can be improved by gradually increasing the control voltage. This is a result leading to a robust and tolerant system in real situation.