Trainable Associative Memory Neural Networks in a Quantum-Dot Cellular Automata

TL;DR

This paper demonstrates the feasibility of implementing high-speed, high-density associative memory neural networks using quantum-dot cellular automata, with promising simulation results for large-scale applications.

Contribution

It introduces a novel design of trainable associative memory neural networks on QCAs, achieving unprecedented density and speed for such systems.

Findings

Successful simulation of associative memory in small neuron arrays

High-density memory potential of 28GB/cm^2

Feasibility of large-scale quantum-dot neural networks

Abstract

Quantum-dot cellular automata (QCAs) offer a diffusive computing paradigm with picosecond transmission speed, making them an ideal candidate for moving diffusive computing to real-world applications. By implementing a trainable associative memory neural network into this substrate, we demonstrate that high-speed, high-density associative memory is feasible through QCAs. The presented design occupies $415\text{nm}^2$ per neuron, which translates to circa $240 \text{ billion neurons/cm}^2$, or $28\text{GB/cm}^2$ of memory storage, offering a real possibility for large-scale associative memory circuits. Results are presented from simulation, demonstrating correct working behaviour of the associative memory in single neurons, two-neuron and four-neuron arrays.