Cellular Memristive-Output Reservoir (CMOR)

TL;DR

This paper presents the design, fabrication, and testing of a fully integrated CMOS-based reservoir computing circuit called CMOR, utilizing cellular automata and memristive memory for non-linear classification tasks.

Contribution

It introduces a novel monolithic reservoir computing circuit with integrated programmable read-out, combining cellular automata and ReRAM in 65-nm CMOS technology.

Findings

Successful electrical testing of the CMOR circuit

Verification of non-linear classification capability

Demonstration of integrated, programmable read-out layer

Abstract

Reservoir computing is a subfield of machine learning in which a complex system, or 'reservoir,' uses complex internal dynamics to non-linearly project an input into a higher-dimensional space. A single trainable output layer then inspects this high-dimensional space for features relevant to perform the given task, such as a classification. Initially, reservoirs were often constructed from recurrent neural networks, but reservoirs constructed from many different elements have been demonstrated. Elementary cellular automata (CA) are one such system which have recently been demonstrated as a powerful and efficient basis which can be used to construct a reservoir. To investigate the feasibility and performance of a monolithic reservoir computing circuit with a fully integrated, programmable read-out layer, we designed, fabricated, and tested a full-custom reservoir computing circuit. This design, the cellular memristive-output reservoir (CMOR), is implemented in 65-nm CMOS technology with integrated front-end-of-the-line (FEOL) resistive random-access memory (ReRAM) used to construct a trainable output layer. We detail the design of this system and present electrical test results verifying its operation and capability to carry out non-linear classifications.