Scalable platform enabling reservoir computing with nanoporous oxide memristors for image recognition and time series prediction

TL;DR

This paper demonstrates a scalable reservoir computing platform using nanoporous oxide memristors for efficient image recognition and time series prediction, mimicking neural connectivity with random, recurrent, and memory features.

Contribution

It introduces a niobium oxide-based memristor with intrinsic structural randomness for reservoir computing, enabling on-chip neuromorphic systems for processing spatiotemporal signals.

Findings

Successful XOR, image recognition, and time series prediction tasks

Achieved high accuracy in Lorenz-63 chaotic time series reconstruction

Potential for energy-efficient, scalable neuromorphic devices

Abstract

Typical mammal brains have some form of random connectivity between neurons. Reservoir computing, a neural network approach, uses random weights within its processing layer along with built-in recurrent connections and short-term, fading memory, and is shown to be time and training efficient in processing spatiotemporal signals. Here we prepared a niobium oxide-based thin film memristor device with intrinsic structural in-homogeneity in the form of random nanopores and performed computational tasks of XOR operations, image recognition, and time series prediction and reconstruction. For the latter task we chose a complex three-dimensional chaotic Lorenz-63 time series. By applying three temporal voltage waveforms individually across the device and training the readout layer with electrical current signals from a three-output physical reservoir, we achieved satisfactory prediction and reconstruction accuracy in comparison to the case of no reservoir. This work highlights the potential for scalable, on-chip devices using all-oxide reservoir systems, paving the way for energy-efficient neuromorphic electronics dealing with time signals.