Quantum Superposition Inspired Spiking Neural Network
This addresses the challenge of improving neural network robustness for AI applications, though it appears incremental as it builds on existing spiking neural networks with quantum-inspired modifications.
The paper tackles the problem of neural networks' performance dropping with changes in data statistics, such as reversing image backgrounds, by proposing a quantum superposition spiking neural network (QS-SNN) that integrates quantum theory with brain-inspired models. The result is more robust performance compared to traditional ANNs, particularly for noisy inputs.
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.