Cognitive Memory Network

TL;DR

This paper introduces a resistive memory network with a hierarchical modular architecture that demonstrates cognitive functions like character recognition, overcoming hardware limitations of traditional neural networks through evolutionary training.

Contribution

It presents a novel resistive memory network architecture that is hardware-efficient and capable of cognitive tasks, trained via evolutionary processes.

Findings

Successfully recognized noisy, rotated, scaled, and shifted characters

Demonstrated hardware advantages over conventional neural networks

Validated cognitive functionality through character recognition

Abstract

A resistive memory network that has no crossover wiring is proposed to overcome the hardware limitations to size and functional complexity that is associated with conventional analogue neural networks. The proposed memory network is based on simple network cells that are arranged in a hierarchical modular architecture. Cognitive functionality of this network is demonstrated by an example of character recognition. The network is trained by an evolutionary process to completely recognise characters deformed by random noise, rotation, scaling and shifting