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

Bulletin of the American Physical Society

Analyzing quantum chaos in three-body systems with machine learning

David E. Huber, Oleksandr V. Marchukov, H.‐W. Hammer, Artem G. Volosniev

Published Jun 2, 2021• 0 citations
OpenAlex

Related papers

Chaos in quantum many-body systems

Gary E. Mitchell

Bulletin of the American Physical Society•Oct 28, 2006•1 citation

Revealing quantum chaos with machine learning

Yaroslav A. Kharkov, Vadim Sotskov, Anton Karazeev +2 more

Understanding properties of quantum matter is an outstanding challenge in science. In this paper, we demonstrate how machine-learning methods can be successfully applied for the classification of various regimes in single-particle and many-body systems. We realize neural network algorithms that perform a classification between regular and chaotic behavior in quantum billiard models with remarkably high accuracy. We use the variational autoencoder for autosupervised classification of regular/chaotic wave functions, as well as demonstrating that autoencoders could be used as a tool for detection of anomalous quantum states, such as quantum scars. By taking this method further, we show that machine-learning techniques allow us to pin down the transition from integrability to many-body quantum chaos in Heisenberg XXZ spin chains. For both cases, we confirm the existence of universal W shapes that characterize the transition. Our results pave the way for exploring the power of machine-learning tools for revealing exotic phenomena in quantum many-body systems.

arXiv:1902.09216•Physical review. B./Physical review. B•Feb 5, 2020•32 citations

Reservoir Computing: From Classical Edge of Chaos to Quantum Dynamical Phases

Lili Ye, Ying‐Cheng Lai

Reservoir computing is a temporal machine-learning architecture particularly suitable for learning and predicting complex nonlinear dynamical systems. A classicalreservoir computer is typically trained to act as a self-evolving dynamical system and its performance can often be maximized at the “edge of chaos.” Extending thisparadigm to quantum systems reveals a broader landscape of physical phenomena. Bridging machine-learning theory and quantum condensed matter physics, thisPerspective synthesizes a unifying framework where the computational power of both classical and quantum reservoirs is fundamentally governed by their dynamical phases. In particular, how quantum phases, such as many-body localized versus ergodic, dictate memory-nonlinearity trade-offs is analyzed. A roadmap for parameter-adaptable quantum AI, transforming encoding, readout, and noise bottlenecks into scalable computational resources is outlined.

•Jun 29, 2026•0 citations

Machine Learning for Quantum Many-body Problems

Yusuke Nomura

電子情報通信学会誌•Nov 1, 2021•0 citations

Machine learning, quantum chaos, and pseudorandom evolution

Daniel W. F. Alves, Michael O. Flynn

By modeling quantum chaotic dynamics with ensembles of random operators, we explore how machine learning algorithms can be used to detect pseudorandom behavior in qubit systems. We analyze samples consisting of pieces of correlation functions and find that machine learning algorithms are capable of determining the degree of pseudorandomness which a system is subject to in a precise sense. This is done without computing any correlators explicitly. Interestingly, even samples drawn from two-point functions are found to be sufficient to solve this classification problem. This presents the possibility of using deep learning algorithms to explore late time behavior in chaotic quantum systems which have been inaccessible to simulation.

arXiv:1808.10498•Physical Review A•May 27, 2020•3 citations

Dynamical Chaos and Many-Body Quantum Systems

Pierre Gaspard

Springer eBooks•Jan 1, 1992•10 citations
Understanding properties of quantum matter is an outstanding challenge in science. In this paper, we demonstrate how machine-learning methods can be successfully applied for the classification of various regimes in single-particle and many-body systems. We realize neural network algorithms that perform a classification between regular and chaotic behavior in quantum billiard models with remarkably high accuracy. We use the variational autoencoder for autosupervised classification of regular/chaotic wave functions, as well as demonstrating that autoencoders could be used as a tool for detection of anomalous quantum states, such as quantum scars. By taking this method further, we show that machine-learning techniques allow us to pin down the transition from integrability to many-body quantum chaos in Heisenberg XXZ spin chains. For both cases, we confirm the existence of universal W shapes that characterize the transition. Our results pave the way for exploring the power of machine-learning tools for revealing exotic phenomena in quantum many-body systems.
Reservoir computing is a temporal machine-learning architecture particularly suitable for learning and predicting complex nonlinear dynamical systems. A classicalreservoir computer is typically trained to act as a self-evolving dynamical system and its performance can often be maximized at the “edge of chaos.” Extending thisparadigm to quantum systems reveals a broader landscape of physical phenomena. Bridging machine-learning theory and quantum condensed matter physics, thisPerspective synthesizes a unifying framework where the computational power of both classical and quantum reservoirs is fundamentally governed by their dynamical phases. In particular, how quantum phases, such as many-body localized versus ergodic, dictate memory-nonlinearity trade-offs is analyzed. A roadmap for parameter-adaptable quantum AI, transforming encoding, readout, and noise bottlenecks into scalable computational resources is outlined.
By modeling quantum chaotic dynamics with ensembles of random operators, we explore how machine learning algorithms can be used to detect pseudorandom behavior in qubit systems. We analyze samples consisting of pieces of correlation functions and find that machine learning algorithms are capable of determining the degree of pseudorandomness which a system is subject to in a precise sense. This is done without computing any correlators explicitly. Interestingly, even samples drawn from two-point functions are found to be sufficient to solve this classification problem. This presents the possibility of using deep learning algorithms to explore late time behavior in chaotic quantum systems which have been inaccessible to simulation.