Quantum Superposition Inspired Spiking Neural Network

TL;DR

This paper introduces a quantum superposition inspired spiking neural network that enhances robustness in processing noisy and reversed images by integrating quantum principles with brain-inspired models.

Contribution

It proposes a novel QS-SNN model combining quantum theory with brain-inspired neural networks to improve robustness against data variations.

Findings

QS-SNN outperforms traditional ANNs on noisy and reversed image tasks.

Quantum-inspired mechanisms enhance neural network robustness.

The model offers insights for future brain-inspired AI development.

Abstract

Despite advances in artificial intelligence models, neural networks still cannot achieve human performance, partly due to differences in how information is encoded and processed compared to human brain. Information in an artificial neural network (ANN) is represented using a statistical method and processed as a fitting function, enabling handling of structural patterns in image, text, and speech processing. However, substantial changes to the statistical characteristics of the data, for example, reversing the background of an image, dramatically reduce the performance. Here, we propose a quantum superposition spiking neural network (QS-SNN) inspired by quantum mechanisms and phenomena in the brain, which can handle reversal of image background color. The QS-SNN incorporates quantum theory with brain-inspired spiking neural network models from a computational perspective, resulting in more robust performance compared with traditional ANN models, especially when processing noisy inputs. The results presented here will inform future efforts to develop brain-inspired artificial intelligence.