Storage properties of a quantum perceptron
Driven by growing computational power and algorithmic developments, machine learning methods have become valuable tools for analyzing vast amounts of data. Simultaneously, the fast technological progress of quantum information processing suggests employing quantum hardware for machine learning purposes. Recent works discuss different architectures of quantum perceptrons, but the abilities of such quantum devices remain debated. Here, we investigate the storage capacity of a particular quantum perceptron architecture by using statistical mechanics techniques and connect our analysis to the theory of classical spin glasses. Specifically, we focus on one concrete quantum perceptron model and explore its storage properties in the limit of a large number of inputs.
Authors
- Aikaterini Gratsea (ORCID: https://orcid.org/0000-0001-8935-796X)
- Maciej Lewenstein (ORCID: https://orcid.org/0000-0002-0210-7800)
- Valentin Kasper (ORCID: https://orcid.org/0000-0001-7687-663X)
Institutions
- Institució Catalana de Recerca i Estudis Avançats (ES)
- Institute of Photonic Sciences (ES)
Publication Details
- Journal
- Physical review. E
- Published
- 2024-08-20
- DOI
- https://doi.org/10.1103/physreve.110.024127
- Citations
- 3
- Primary Topic
- Neural Networks and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.69
Funders
- Fundación Cellex
- Institut de Ciències Fotòniques
- European Commission
- Generalitat de Catalunya
- Federación Española de Enfermedades Raras
- Barcelona Supercomputing Center
- FUNDACIÓ Privada MIR-PUIG
- European Research Council
- Agència de Gestió d'Ajuts Universitaris i de Recerca
- Horizon 2020
- European Regional Development Fund
- HORIZON EUROPE Marie Sklodowska-Curie Actions