Quantum Superposition Inspired Spiking Neural Network
arXiv:2010.12197 · doi:10.1016/j.isci.2021.102880
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.
References in corpus (15)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Quantum algorithm for solving linear systems of equations
- Quantum principal component analysis
- Efficient Learning for Deep Quantum Neural Networks
- The quest for a Quantum Neural Network
- SLAYER: Spike Layer Error Reassignment in Time
- Simulating a perceptron on a quantum computer
- Quantum Neuron: an elementary building block for machine learning on quantum computers
- Unitary quantum perceptron as efficient universal approximator
- Quantum coherence in ion channels: Resonances, Transport and Verification
- Quantum computing model of an artificial neuron with continuously valued input data
- Image Processing in Quantum Computers
- Quantum Image Processing: the truth, the whole truth, and nothing but the truth about its problems on internal image representation and outcomes recovering
- Analysis of five techniques for the internal representation of a digital image inside a quantum processor