Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2509.18262 · Physical Review A

Training the classification capability of large-scale quantum cellular automata

Mario Boneberg, Simon Kochsiek, Gabriele Perfetto, Igor Lesanovsky

Published Jun 1, 2026• 2 citations
arXivHTMLPDF

Abstract

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.

DOI
10.1103/gds1-9vhy

Related papers

Using (1+1)D quantum cellular automata for exploring collective effects in large-scale quantum neural networks

Edward Gillman, Federico Carollo, Igor Lesanovsky

Central to the field of quantum machine learning is the design of quantum perceptrons and neural network architectures. A key question in this regard is the impact of quantum effects on the way such models process information. Here, we establish a connection between (1+1)D quantum cellular automata, which implement a discrete nonequilibrium quantum many-body dynamics through successive applications of local quantum gates, and quantum neural networks (QNNs), which process information by feeding it through perceptrons interconnecting adjacent layers. Exploiting this link, we construct a class of QNNs that are highly structured-aiding both interpretability and helping to avoid trainability issues in machine learning tasks-yet can be connected rigorously to continuous-time Lindblad dynamics. We further analyze the universal properties of an example case, identifying a change of critical behavior when quantum effects are varied, showing their potential impact on the collective dynamical behavior underlying information processing in large-scale QNNs.

arXiv:2207.11777•Physical review. E•Feb 22, 2023•13 citations

Nonlinear classification capability of quantum neural networks due to emergent quantum metastability

Mario Boneberg, Federico Carollo, Igor Lesanovsky

The power and expressivity of deep classical neural networks can be attributed to nonlinear input-output relations. Such nonlinearities are at the heart of many computational tasks, such as data classification and pattern recognition. Quantum neural networks, on the other hand, are necessarily linear as they process information via unitary operations. Here we show that effective nonlinearities can be implemented in these platforms by exploiting the relationship between information processing and many-body quantum dynamics. The crucial point is that quantum many-body systems can show emergent collective behavior in the vicinity of phase transitions, which leads to an effectively nonlinear dynamics in the thermodynamic limit. In the context of quantum neural networks, which are necessarily finite, this translates into metastability with transient nonergodic behavior. By using a quantum neural network the architecture of which is inspired by dissipative many-body quantum spin models, we show that this mechanism indeed allows one to realize nonlinear data classification, despite the underlying dynamics being local and linear. Our proof-of-principle study may pave the way for the systematic construction of quantum neural networks with emergent nonlinear properties.

arXiv:2408.10765•Physical Review A•Jun 4, 2025•5 citations

Ergodicity breaking for data classification in a dissipative Ising model with competing two- and four-body interactions

Simon Kochsiek, Mario Boneberg, Igor Lesanovsky

We explore the close relationship between the processing of data and the dynamics of interacting many-body systems. For example, certain classes of quantum neural networks can be mapped onto dissipative quantum Ising models whose evolution is described by a Lindblad master equation. In these architectures, emergent nonlinearities lead to non-ergodic dynamics under which initial states located in different basins of attraction evolve towards distinguishable stationary states. This mechanism underlies the classification of quantum data. Motivated by this connection, we consider an Ising model with competing two- and four-body interactions. Using a combination of mean-field calculations and exact small-scale numerics, we show that the stationary state manifold can be designed to enable multi-class classification. We also investigate the structure of the ensuing basins of attraction, thereby showing that these systems allow for the classification of quantum states with nonlinear decision boundaries.

arXiv:2611.17036•Nov 12, 2026•0 citations

Dissipative quantum many-body dynamics in (1+1)D quantum cellular automata and quantum neural networks

Mario Boneberg, Federico Carollo, Igor Lesanovsky

Abstract Classical artificial neural networks, built from elementary units, possess enormous expressive power. Here we investigate a quantum neural network (QNN) architecture, which follows a similar paradigm. It is structurally equivalent to so-called (1+1)D quantum cellular automata, which are two-dimensional quantum lattice systems on which dynamics takes place in discrete time. Information transfer between consecutive time slices—or adjacent network layers—is governed by local quantum gates, which can be regarded as the quantum counterpart of the classical elementary units. Along the time-direction an effective dissipative evolution emerges on the level of the reduced state, and the nature of this dynamics is dictated by the structure of the elementary gates. We show how to construct the local unitary gates to yield a desired many-body dynamics, which in certain parameter regimes is governed by a Lindblad master equation. We study this for small system sizes through numerical simulations and demonstrate how collective effects within the quantum cellular automaton can be controlled parametrically. Our study constitutes a step towards the utilization of large-scale emergent phenomena in large QNNs for machine learning purposes.

arXiv:2304.11209•New Journal of Physics•Aug 14, 2023•7 citations

Getting large-scale quantum neural networks ready for quantum hardware

Mario Boneberg, Simon Kochsiek, Igor Lesanovsky

Quantum neural networks generalize classical artificial neural networks into the quantum domain. They are formulated as parameterized quantum circuits which are optimized by measuring and minimizing a suitably chosen loss function. The core challenge in understanding, implementing and ultimately using quantum neural networks is that they represent many-body systems with an exponentially large Hilbert space, in combination with a large parameter search space. Moreover, noise -- which is inherent to any quantum measurement -- sets practical limits for the estimation of training loss. Here, we study physics-informed large-scale quantum neural networks that are trained through a finite number of noisy loss function measurements. We show that this architecture permits the construction of nontrivial decision boundaries that enable the classification of quantum states through measuring an order parameter. Our approach can directly process quantum data that is output from quantum simulators and computers and is well suited for implementation on current hardware. Moreover, owed to a close link between the neural network dynamics and the evolution of Markovian open many-body quantum systems, one may expect a certain robustness to noise, which is ubiquitous in the current NISQ era.

quant-pharXiv:2604.24886•Apr 29, 2026•1 citation

Quantum neural networks to detect entanglement transitions in quantum many-body systems

F. El Ayachi, Hicham Ait Mansour, M. El Baz

Abstract Quantum entanglement becomes increasingly complex to analyze in many-body systems due to exponential growth in complexity with system size. In this work, we explore the potential of quantum machine learning (QML) to circumvent this. Specifically, we train a parameterized quantum neural network (QNN) model to detect transitions in the entanglement properties of the ground state in a multi-spin Ising model. This approach enables the classification of different entanglement states and provides deeper insights into the behavior of entanglement under multi-spin interactions. Our results demonstrate that QML can effectively simplify the classification process and overcome the complexity challenges encountered by classical algorithms.

Physica Scripta•Nov 18, 2024•3 citations
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 Z2\mathbb{Z}_2Z2​-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.
Central to the field of quantum machine learning is the design of quantum perceptrons and neural network architectures. A key question in this regard is the impact of quantum effects on the way such models process information. Here, we establish a connection between (1+1)D quantum cellular automata, which implement a discrete nonequilibrium quantum many-body dynamics through successive applications of local quantum gates, and quantum neural networks (QNNs), which process information by feeding it through perceptrons interconnecting adjacent layers. Exploiting this link, we construct a class of QNNs that are highly structured-aiding both interpretability and helping to avoid trainability issues in machine learning tasks-yet can be connected rigorously to continuous-time Lindblad dynamics. We further analyze the universal properties of an example case, identifying a change of critical behavior when quantum effects are varied, showing their potential impact on the collective dynamical behavior underlying information processing in large-scale QNNs.
The power and expressivity of deep classical neural networks can be attributed to nonlinear input-output relations. Such nonlinearities are at the heart of many computational tasks, such as data classification and pattern recognition. Quantum neural networks, on the other hand, are necessarily linear as they process information via unitary operations. Here we show that effective nonlinearities can be implemented in these platforms by exploiting the relationship between information processing and many-body quantum dynamics. The crucial point is that quantum many-body systems can show emergent collective behavior in the vicinity of phase transitions, which leads to an effectively nonlinear dynamics in the thermodynamic limit. In the context of quantum neural networks, which are necessarily finite, this translates into metastability with transient nonergodic behavior. By using a quantum neural network the architecture of which is inspired by dissipative many-body quantum spin models, we show that this mechanism indeed allows one to realize nonlinear data classification, despite the underlying dynamics being local and linear. Our proof-of-principle study may pave the way for the systematic construction of quantum neural networks with emergent nonlinear properties.
We explore the close relationship between the processing of data and the dynamics of interacting many-body systems. For example, certain classes of quantum neural networks can be mapped onto dissipative quantum Ising models whose evolution is described by a Lindblad master equation. In these architectures, emergent nonlinearities lead to non-ergodic dynamics under which initial states located in different basins of attraction evolve towards distinguishable stationary states. This mechanism underlies the classification of quantum data. Motivated by this connection, we consider an Ising model with competing two- and four-body interactions. Using a combination of mean-field calculations and exact small-scale numerics, we show that the stationary state manifold can be designed to enable multi-class classification. We also investigate the structure of the ensuing basins of attraction, thereby showing that these systems allow for the classification of quantum states with nonlinear decision boundaries.
Abstract Classical artificial neural networks, built from elementary units, possess enormous expressive power. Here we investigate a quantum neural network (QNN) architecture, which follows a similar paradigm. It is structurally equivalent to so-called (1+1)D quantum cellular automata, which are two-dimensional quantum lattice systems on which dynamics takes place in discrete time. Information transfer between consecutive time slices—or adjacent network layers—is governed by local quantum gates, which can be regarded as the quantum counterpart of the classical elementary units. Along the time-direction an effective dissipative evolution emerges on the level of the reduced state, and the nature of this dynamics is dictated by the structure of the elementary gates. We show how to construct the local unitary gates to yield a desired many-body dynamics, which in certain parameter regimes is governed by a Lindblad master equation. We study this for small system sizes through numerical simulations and demonstrate how collective effects within the quantum cellular automaton can be controlled parametrically. Our study constitutes a step towards the utilization of large-scale emergent phenomena in large QNNs for machine learning purposes.
Quantum neural networks generalize classical artificial neural networks into the quantum domain. They are formulated as parameterized quantum circuits which are optimized by measuring and minimizing a suitably chosen loss function. The core challenge in understanding, implementing and ultimately using quantum neural networks is that they represent many-body systems with an exponentially large Hilbert space, in combination with a large parameter search space. Moreover, noise -- which is inherent to any quantum measurement -- sets practical limits for the estimation of training loss. Here, we study physics-informed large-scale quantum neural networks that are trained through a finite number of noisy loss function measurements. We show that this architecture permits the construction of nontrivial decision boundaries that enable the classification of quantum states through measuring an order parameter. Our approach can directly process quantum data that is output from quantum simulators and computers and is well suited for implementation on current hardware. Moreover, owed to a close link between the neural network dynamics and the evolution of Markovian open many-body quantum systems, one may expect a certain robustness to noise, which is ubiquitous in the current NISQ era.
Abstract Quantum entanglement becomes increasingly complex to analyze in many-body systems due to exponential growth in complexity with system size. In this work, we explore the potential of quantum machine learning (QML) to circumvent this. Specifically, we train a parameterized quantum neural network (QNN) model to detect transitions in the entanglement properties of the ground state in a multi-spin Ising model. This approach enables the classification of different entanglement states and provides deeper insights into the behavior of entanglement under multi-spin interactions. Our results demonstrate that QML can effectively simplify the classification process and overcome the complexity challenges encountered by classical algorithms.