Protein Structured Reservoir computing for Spike-based Pattern Recognition

TL;DR

This paper proposes a novel reservoir computing system based on a single protein molecule with neuromorphic connectivity, demonstrating its potential for pattern recognition tasks like handwritten digit classification.

Contribution

It introduces a protein-structured reservoir computing architecture using a single molecule with small-world connectivity for spike-based pattern recognition.

Findings

Achieved acceptable classification accuracy on MNIST dataset.

Demonstrated feasibility of molecular reservoir computing with neuromorphic connectivity.

Compared performance with other approaches showing competitive results.

Abstract

Nowadays we witness a miniaturisation trend in the semiconductor industry backed up by groundbreaking discoveries and designs in nanoscale characterisation and fabrication. To facilitate the trend and produce ever smaller, faster and cheaper computing devices, the size of nanoelectronic devices is now reaching the scale of atoms or molecules - a technical goal undoubtedly demanding for novel devices. Following the trend, we explore an unconventional route of implementing a reservoir computing on a single protein molecule and introduce neuromorphic connectivity with a small-world networking property. We have chosen Izhikevich spiking neurons as elementary processors, corresponding to the atoms of verotoxin protein, and its molecule as a 'hardware' architecture of the communication networks connecting the processors. We apply on a single readout layer various training methods in a supervised fashion to investigate whether the molecular structured Reservoir Computing (RC) system is capable to deal with machine learning benchmarks. We start with the Remote Supervised Method, based on Spike-Timing-Dependent-Plasticity, and carry on with linear regression and scaled conjugate gradient back-propagation training methods. The RC network is evaluated as a proof-of-concept on the handwritten digit images from the MNIST dataset and demonstrates acceptable classification accuracy in comparison with other similar approaches.