On a quantum inspired approach to train machine learning models

Abstract In this work, a novel technique to train machine learning models is introduced, which is based on digital simulations of certain types of quantum systems. This represents a drastic departure from the standard approach of quantum machine learning which, to this day, is based on the use of ac...

Volledige beschrijving

Bibliografische gegevens
Hoofdauteur: Jean Michel Sellier
Formaat: Artikel
Taal:English
Gepubliceerd in: Wiley 2023-12-01
Reeks:Applied AI Letters
Onderwerpen:
Online toegang:https://doi.org/10.1002/ail2.89
Omschrijving
Samenvatting:Abstract In this work, a novel technique to train machine learning models is introduced, which is based on digital simulations of certain types of quantum systems. This represents a drastic departure from the standard approach of quantum machine learning which, to this day, is based on the use of actual physical quantum systems. To provide a clear context, the field of quantum inspired machine learning is first provided. Then, we proceed with a detailed description of our proposed method. To conclude, some preliminary, yet compelling, results are presented and discussed. Although at a seminal stage, the author firmly believes that this approach could represent a valid and robust alternative to the way machine learning models are trained today.
ISSN:2689-5595