Highly reliable resistive switching memory for neuromorphic computing and artificial visual system
발표자
()
초록
내용
In this talk, an analog memristor with 3D ion transport channels, which can provide unprecedentedly high reliability and robustness for neuromorphic hardware-implementation, is introduced. This architecture is compatible with back-end-of-line process and flexible format. Based on its superior characteristics, a practical adaptive learning rule is designed and a neural network that can perform the biological tissue classification task using the ultrasound signals is proposed. I also introduce a strategy that can universally provide a color-selective synaptic functionality into a two-terminal memristor regardless of the kinds of switching medium for artificial visual system.