Quantum neuron with real weights
This paper proposes a new model of a real weights quantum neuron exploiting the so-called quantum parallelism which allows for an exponential speedup of computations. The quantum neurons were trained in a classical–quantum approach, considering the delta rule to update the values of the weights in a...
Gespeichert in:
Veröffentlicht in: | Neural networks 2021-11, Vol.143, p.698-708 |
---|---|
Hauptverfasser: | , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | This paper proposes a new model of a real weights quantum neuron exploiting the so-called quantum parallelism which allows for an exponential speedup of computations. The quantum neurons were trained in a classical–quantum approach, considering the delta rule to update the values of the weights in an image database of three distinct patterns. We performed classical simulations and also executed experiments in an actual small-scale quantum processor. The results of the experiments show that the proposed quantum real neuron model has a good generalisation capacity, demonstrating better accuracy than the traditional binary quantum perceptron model. |
---|---|
ISSN: | 0893-6080 1879-2782 |
DOI: | 10.1016/j.neunet.2021.07.034 |