Experimental Robust Spontaneous Synchronizations in Coupled NbOx Oscillation Neurons for Unconventional Computing
IEEE TRANSACTIONS ON ELECTRON DEVICES(2023)
摘要
In this brief, we demonstrate experimentally achieved oscillation dynamics in coupled NbOx thresholds witch (TS)-based oscillation neurons (ONs). We first show the challenges in observing oscillation caused by devicevariability, which is further validated through HSPICE simulations. To obtain robust oscillation response, a reliable TS developed via atomic layer deposition for conformal NbOx is introduced. By developing coupled NbO(x )ONs using acoupling resistor (RC), the out-of-phase synchronizationis demonstrated owing to the weak connection. Moreover,we achieve a transition to in-phase synchronization as the coupling strength increases, showing an inverse relation-ship with the magnitude of R-C. Based on these results,oscillatory neural networks, where multiple NbO(x )ONs arefully connected, are examined to execute pattern recognition via MATALB simulations
更多查看译文
关键词
Image processing, oscillatory neural network (ONN), NbOx, threshold switching
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要