Affiliation:
1. Department of Materials Science and Engineering and Inter‐university Semiconductor Research Center, College of Engineering Seoul National University Seoul 08826 Republic of Korea
2. Mechatronics Research Center Samsung Electronics, Banwal‐dong Hwasung‐si Gyeonggi‐do 18448 Republic of Korea
Abstract
AbstractMemristor‐based physical reservoir computing (RC) is a robust framework for processing complex spatiotemporal data parallelly. However, conventional memristor‐based reservoirs cannot capture the spatial relationship between the time‐varying inputs due to the specific mapping scheme assigning one input signal to one memristor conductance. Here, a physical “graph reservoir” is introduced using a metal cell at the diagonal‐crossbar array (mCBA) with dynamic self‐rectifying memristors. Input and inverted input signals are applied to the word and bit lines of the mCBA, respectively, storing the correlation information between input signals in the memristors. In this way, the mCBA graph reservoirs can map the spatiotemporal correlation of the input data in a high‐dimensional feature space. The high‐dimensional mapping characteristics of the graph reservoir achieve notable results, including a normalized root‐mean‐square error of 0.09 in Mackey–Glass time series prediction, a 97.21% accuracy in MNIST recognition, and an 80.0% diagnostic accuracy in human connectome classification.
Funder
National Research Foundation of Korea
Subject
Mechanical Engineering,Mechanics of Materials,General Materials Science
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献