| 主页 > Classification with Integrated Quantum and Spiking Neural Networks |
| Article | |
| Title | Classification with Integrated Quantum and Spiking Neural Networks |
| Author(s) | Pasquali, Dominic (UC, Santa Cruz ; CERN) ; Grossi, Michele (CERN) ; Vallecorsa, Sofia (CERN) |
| Publication | 2023 |
| Number of pages | 2 |
| In: | 2023 International Conference on Quantum Computing and Engineering (QCE23), Bellevue, United States, 17 - 22 Sep 2023, pp.298-299 |
| DOI | 10.1109/QCE57702.2023.10251 |
| Subject category | Quantum Technology |
| Abstract | Spiking neural networks are rapidly gaining interest in analogue computation. So far little work has been conducted in blending quantum and spiking neural network methods into machine learning models. First of their kind methods to embed quantum machine learning techniques between spiking network layers are proposed and benchmarked against similar purely classical spiking models. It's found that all proposed methods achieve a higher accuracy faster on training and test data than comparable classical spiking models. These approaches demonstrate the ability for traditional quantum machine learning methods to be easily integrated into and improve spiking neural network performance. The presented results and behavior will be discussed. |