Training the classification capability of large-scale quantum cellular automata

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Boneberg, Mario, Kochsiek, Simon, Perfetto, Gabriele, Lesanovsky, Igor
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866916961656504320
author Boneberg, Mario
Kochsiek, Simon
Perfetto, Gabriele
Lesanovsky, Igor
author_facet Boneberg, Mario
Kochsiek, Simon
Perfetto, Gabriele
Lesanovsky, Igor
contents In the vicinity of a phase transition ergodicity can be broken. Here, different initial many-body configurations evolve towards one of several fixed points, which are macroscopically distinguishable through an order parameter. This mechanism enables state classification in quantum cellular automata and feed-forward quantum neural networks. We demonstrate that this capability can be efficiently learned from training data even in extremely high-dimensional state spaces. We illustrate this using a quantum cellular automaton that allows binary classification, which is closely connected to the dynamics of a $\mathbb{Z}_2$-symmetric Ising model with local interactions and dissipation. This approach can be generalized beyond binary classification and offers a natural framework for exploring the link between emergent many-body phenomena and the interpretation of data processing capabilities in the context of quantum machine learning.
format Preprint
id arxiv_https___arxiv_org_abs_2509_18262
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Training the classification capability of large-scale quantum cellular automata
Boneberg, Mario
Kochsiek, Simon
Perfetto, Gabriele
Lesanovsky, Igor
Quantum Physics
Disordered Systems and Neural Networks
Statistical Mechanics
In the vicinity of a phase transition ergodicity can be broken. Here, different initial many-body configurations evolve towards one of several fixed points, which are macroscopically distinguishable through an order parameter. This mechanism enables state classification in quantum cellular automata and feed-forward quantum neural networks. We demonstrate that this capability can be efficiently learned from training data even in extremely high-dimensional state spaces. We illustrate this using a quantum cellular automaton that allows binary classification, which is closely connected to the dynamics of a $\mathbb{Z}_2$-symmetric Ising model with local interactions and dissipation. This approach can be generalized beyond binary classification and offers a natural framework for exploring the link between emergent many-body phenomena and the interpretation of data processing capabilities in the context of quantum machine learning.
title Training the classification capability of large-scale quantum cellular automata
topic Quantum Physics
Disordered Systems and Neural Networks
Statistical Mechanics
url https://arxiv.org/abs/2509.18262