Spatiotemporal Data Processing with Memristor Crossbar-Array-Based Graph Reservoir

Abstract

Memristor-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. A physical "graph reservoir" is implemented using a metal cell at the diagonal-crossbar array (mCBA) structure and dynamic self-rectifying memristors. Spatiotemporal correlation information is extracted from mCBA using a unique mapping method called "inverted encoding." Spatial (image recognition), temporal (time series prediction), and spatiotemporal (attention-deficit/hyperactivity disorder (ADHD) classification) analysis are effectively performed based on the graph reservoir.image