{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:24:41Z","timestamp":1777508681552,"version":"3.51.4"},"reference-count":78,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T00:00:00Z","timestamp":1671148800000},"content-version":"vor","delay-in-days":15,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T00:00:00Z","timestamp":1671148800000},"content-version":"tdm","delay-in-days":15,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"ETH Foundation","award":["Excellence Scholarship & Opportunity Programme"],"award-info":[{"award-number":["Excellence Scholarship & Opportunity Programme"]}]},{"DOI":"10.13039\/501100001711","name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung","doi-asserted-by":"crossref","award":["200020_165843"],"award-info":[{"award-number":["200020_165843"]}],"id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Austrian Science Fund","award":["DK-ALM: W1259-N27"],"award-info":[{"award-number":["DK-ALM: W1259-N27"]}]},{"DOI":"10.13039\/501100001822","name":"Austrian Academy of Sciences","doi-asserted-by":"crossref","award":["DOC Fellowship"],"award-info":[{"award-number":["DOC Fellowship"]}],"id":[{"id":"10.13039\/501100001822","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003542","name":"Ministerium f\u00fcr Wissenschaft, Forschung und Kunst Baden-W\u00fcrttemberg","doi-asserted-by":"crossref","award":["AZ:33- 7533.-30-10\/41\/1"],"award-info":[{"award-number":["AZ:33- 7533.-30-10\/41\/1"]}],"id":[{"id":"10.13039\/501100003542","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Science Foundation","award":["PHY-1125565"],"award-info":[{"award-number":["PHY-1125565"]}]},{"DOI":"10.13039\/501100021847","name":"Centro Svizzero di Calcolo Scientifico","doi-asserted-by":"crossref","award":["da04"],"award-info":[{"award-number":["da04"]}],"id":[{"id":"10.13039\/501100021847","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000936","name":"Gordon and Betty Moore Foundation","doi-asserted-by":"crossref","award":["GBMF-12500028"],"award-info":[{"award-number":["GBMF-12500028"]}],"id":[{"id":"10.13039\/100000936","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>To make progress in science, we often build abstract representations of physical systems that meaningfully encode information about the systems. Such representations ignore redundant features and treat parameters such as velocity and position separately because they can be useful for making statements about different experimental settings. Here, we capture this notion by formally defining the concept of operationally meaningful representations. We present an autoencoder architecture with attention mechanism that can generate such representations and demonstrate it on examples involving both classical and quantum physics. For instance, our architecture finds a compact representation of an arbitrary two-qubit system that separates local parameters from parameters describing quantum correlations.<\/jats:p>","DOI":"10.1088\/2632-2153\/ac9ae8","type":"journal-article","created":{"date-parts":[[2022,10,17]],"date-time":"2022-10-17T22:21:35Z","timestamp":1666045295000},"page":"045025","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":12,"title":["Operationally meaningful representations of physical systems in neural networks"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7815-7006","authenticated-orcid":true,"given":"Hendrik","family":"Poulsen Nautrup","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tony","family":"Metger","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Raban","family":"Iten","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sofiene","family":"Jerbi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lea M","family":"Trenkwalder","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Henrik","family":"Wilming","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hans J","family":"Briegel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renato","family":"Renner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2022,12,16]]},"reference":[{"key":"mlstac9ae8bib1","author":"Nielsen","year":"2018"},{"key":"mlstac9ae8bib2","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"mlstac9ae8bib3","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"Nature"},{"key":"mlstac9ae8bib4","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6633\/aab406","article-title":"Machine learning andartificial intelligence in the quantum domain: a review of recent progress","volume":"81","author":"Dunjko","year":"2018","journal-title":"Rep. Prog. Phys."},{"key":"mlstac9ae8bib5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2976199","article-title":"Explainable machine learning for scientific insights and discoveries","volume":"8","author":"Roscher","year":"2020","journal-title":"IEEE Access"},{"key":"mlstac9ae8bib6","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.91.045002","article-title":"Machine learning and the physical sciences","volume":"91","author":"Carleo","year":"2019","journal-title":"Rev. Mod. Phys."},{"key":"mlstac9ae8bib7","first-page":"p 172","article-title":"Humans predict liquid dynamics using probabilistic simulation","volume":"vol 1","author":"Bates","year":"2015"},{"key":"mlstac9ae8bib8","first-page":"pp 127","article-title":"Galileo: perceiving physical object properties by integrating a physics engine with deep learning","author":"Wu","year":"2015"},{"key":"mlstac9ae8bib9","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.cogpsych.2018.05.001","article-title":"Intuitive experimentation in the physical world","volume":"105","author":"Bramley","year":"2018","journal-title":"Cogn. Psychol."},{"key":"mlstac9ae8bib10","article-title":"Learning generalizable physical dynamics of 3D rigid objects","author":"Rempe","year":"2019"},{"key":"mlstac9ae8bib11","article-title":"Adding intuitive physics to neural-symbolic capsules using interaction networks","author":"Kissner","year":"2019"},{"key":"mlstac9ae8bib12","article-title":"Unsupervised intuitive physics from visual observations","author":"Ehrhardt","year":"2018"},{"key":"mlstac9ae8bib13","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01258-8_6","article-title":"Interpretable intuitive physics model","author":"Ye","year":"2018"},{"key":"mlstac9ae8bib14","article-title":"Unsupervised learning of latent physical properties using perception-prediction networks","author":"Zheng","year":"2018"},{"key":"mlstac9ae8bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.124.010508","article-title":"Discovering physical concepts with neural networks","volume":"124","author":"Iten","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstac9ae8bib16","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1073\/pnas.1714936115","article-title":"Active learning machine learns to create new quantum experiments","volume":"115","author":"Melnikov","year":"2018"},{"key":"mlstac9ae8bib17","article-title":"How a minimal learning agent can infer the existence of unobserved variables in a complex environment","author":"Ried","year":"2019"},{"key":"mlstac9ae8bib18","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1038\/srep00522","article-title":"On creative machines and the physical origins of freedom","volume":"2","author":"Briegel","year":"2012","journal-title":"Sci. Rep."},{"key":"mlstac9ae8bib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.100.033311","article-title":"Toward an artificial intelligence physicist for unsupervised learning","volume":"100","author":"Wu","year":"2019","journal-title":"Phys. Rev. E"},{"key":"mlstac9ae8bib20","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1140\/epjc\/s10052-019-6787-3","article-title":"Guiding new physics searches with unsupervised learning","volume":"79","author":"De Simone","year":"2019","journal-title":"Eur. Phys. J. C"},{"key":"mlstac9ae8bib21","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevD.99.015014","article-title":"Learning new physics from a machine","volume":"99","author":"D\u2019Agnolo","year":"2019","journal-title":"Phys. Rev. D"},{"key":"mlstac9ae8bib22","article-title":"Learning the arrow of time","author":"Rahaman","year":"2019"},{"key":"mlstac9ae8bib23","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","article-title":"Representation learning: a review and new perspectives","volume":"35","author":"Bengio","year":"2012","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstac9ae8bib24","article-title":"Beta-VAE: learning basic visual concepts with a constrained variational framework","author":"Higgins","year":"2017"},{"key":"mlstac9ae8bib25","article-title":"Isolating sources of disentanglement in variational autoencoders","author":"Chen","year":"2018"},{"key":"mlstac9ae8bib26","article-title":"Disentangling by factorising","author":"Kim","year":"2018"},{"key":"mlstac9ae8bib27","article-title":"Disentangling the independently controllable factors of variation by interacting with the world","author":"Thomas","year":"2018"},{"key":"mlstac9ae8bib28","first-page":"p 3582","article-title":"Combined reinforcement learning via abstract representations","author":"Fran\u00e7ois-Lavet","year":"2019"},{"key":"mlstac9ae8bib29","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"mlstac9ae8bib30","author":"Sutton","year":"1998"},{"key":"mlstac9ae8bib31","author":"Paris","year":"2004"},{"key":"mlstac9ae8bib32","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.93.062320","article-title":"Entangled bloch spheres: bloch matrix and two-qubit state space","volume":"93","author":"Gamel","year":"2016","journal-title":"Phys. Rev."},{"key":"mlstac9ae8bib33","doi-asserted-by":"publisher","first-page":"01LT01","DOI":"10.1088\/2632-2153\/ac362b","article-title":"Attention-based quantum tomography","volume":"3","author":"Cha","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstac9ae8bib34","doi-asserted-by":"publisher","first-page":"e10","DOI":"10.23915\/distill.00010","article-title":"The building blocks of interpretability","volume":"3","author":"Olah","year":"2018","journal-title":"Distill"},{"key":"mlstac9ae8bib35","article-title":"The consciousness prior","author":"Bengio","year":"2017"},{"key":"mlstac9ae8bib36","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/s10514-015-9459-7","article-title":"Learning state representations with robotic priors","volume":"39","author":"Jonschkowski","year":"2015","journal-title":"Auton. Robots"},{"key":"mlstac9ae8bib37","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.031084","article-title":"Reinforcement learning with neural networks for quantum feedback","volume":"8","author":"F\u00f6sel","year":"2018","journal-title":"Phys. Rev. X"},{"key":"mlstac9ae8bib38","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.257204","article-title":"Machine learning out-of-equilibrium phases of matter","volume":"120","author":"Venderley","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstac9ae8bib39","article-title":"Quantum circuit optimization with deep reinforcement learning","author":"F\u00f6sel","year":"2021"},{"key":"mlstac9ae8bib40","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/aba947","article-title":"Self-referencing embedded strings (SELFIES): a 100% robust molecular string representation","volume":"1","author":"Krenn","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstac9ae8bib41","article-title":"Translating neuralese","volume":"vol 232","author":"Andreas","year":"2017"},{"key":"mlstac9ae8bib42","article-title":"TensorFlow: large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"key":"mlstac9ae8bib43","article-title":"Automatic differentiation in PyTorch","author":"Paszke","year":"2017"},{"key":"mlstac9ae8bib44","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2015"},{"key":"mlstac9ae8bib45","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.csl.2016.10.006","article-title":"Multi-way, multilingual neural machine translation","volume":"45","author":"Firat","year":"2017","journal-title":"Comput. Speech Lang."},{"key":"mlstac9ae8bib46","article-title":"Deep communicating agents for abstractive summarization","volume":"vol 1662","author":"Celikyilmaz","year":"2018"},{"key":"mlstac9ae8bib47","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2009","journal-title":"IEEE Trans. Neural Netw."},{"key":"mlstac9ae8bib48","first-page":"p 2688","article-title":"Neural relational inference for interacting systems","volume":"vol 80","author":"Kipf","year":"2018"},{"key":"mlstac9ae8bib49","first-page":"pp 4509","article-title":"Interaction networks for learning about objects, relations and physics","author":"Battaglia","year":"2016"},{"key":"mlstac9ae8bib50","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/j.neunet.2018.07.006","article-title":"State representation learning for control: an overview","volume":"108","author":"Lesort","year":"2018","journal-title":"Neural Netw."},{"key":"mlstac9ae8bib51","article-title":"Independently controllable features","author":"Bengio","year":"2017"},{"key":"mlstac9ae8bib52","article-title":"Reinforcement learning with unsupervised auxiliary tasks","author":"Jaderberg","year":"2017"},{"key":"mlstac9ae8bib53","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"mlstac9ae8bib54","first-page":"vol 48 p 1899","article-title":"Graying the black box: understanding DQNs","author":"Zahavy","year":"2016"},{"key":"mlstac9ae8bib55","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1016\/j.scib.2019.07.014","article-title":"Emergent Schr\u00f6dinger equation in an introspective machine learning architecture","volume":"64","author":"Wang","year":"2019","journal-title":"Sci. Bull."},{"key":"mlstac9ae8bib56","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1038\/s42256-019-0028-1","article-title":"Reconstructing quantum states with generative models","volume":"1","author":"Carrasquilla","year":"2019","journal-title":"Nat. Mach. Intell."},{"key":"mlstac9ae8bib57","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.102.042604","article-title":"Neural-network quantum state tomography in a two-qubit experiment","volume":"102","author":"Neugebauer","year":"2020","journal-title":"Phys. Rev. A"},{"key":"mlstac9ae8bib58","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.104.032610","article-title":"Probabilistic simulation of quantum circuits using a deep-learning architecture","volume":"104","author":"Carrasquilla","year":"2021","journal-title":"Phys. Rev. A"},{"key":"mlstac9ae8bib59","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1126\/science.aag2302","article-title":"Solving the quantum many-body problem with artificial neural networks","volume":"355","author":"Carleo","year":"2017","journal-title":"Science"},{"key":"mlstac9ae8bib60","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.011006","article-title":"Neural-network quantum states, string-bond states and chiral topological states","volume":"8","author":"Glasser","year":"2018","journal-title":"Phys. Rev. X"},{"key":"mlstac9ae8bib61","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1038\/srep00400","article-title":"Projective simulation for artificial intelligence","volume":"2","author":"Briegel","year":"2012","journal-title":"Sci. Rep."},{"key":"mlstac9ae8bib62","doi-asserted-by":"publisher","first-page":"215","DOI":"10.22331\/q-2019-12-16-215","article-title":"Optimizing quantum error correction codes with reinforcement learning","volume":"3","author":"Poulsen Nautrup","year":"2019","journal-title":"Quantum"},{"key":"mlstac9ae8bib63","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.1.010301","article-title":"Machine learning for long-distance quantum communication","volume":"1","author":"Walln\u00f6fer","year":"2020","journal-title":"PRX Quantum"},{"key":"mlstac9ae8bib64","first-page":"p 2799","article-title":"Robotic playing for hierarchical complex skill learning","author":"Hangl","year":"2016"},{"key":"mlstac9ae8bib65","article-title":"Skill learning by autonomous robotic playing using active learning and creativity","author":"Hangl","year":"2017"},{"key":"mlstac9ae8bib66","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pone.0212044","article-title":"Modelling collective motion based on the principle of agency: general framework and the case of marching locusts","volume":"14","author":"Ried","year":"2019","journal-title":"PLoS One"},{"key":"mlstac9ae8bib67","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-14740-y","article-title":"Projective simulation with generalization","volume":"7","author":"Melnikov","year":"2017","journal-title":"Sci. Rep."},{"key":"mlstac9ae8bib68","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/ab783c","article-title":"Photonic architecture for reinforcement learning","volume":"22","author":"Flamini","year":"2020","journal-title":"New J. Phys."},{"key":"mlstac9ae8bib69","article-title":"Reinforcement learning through asynchronous advantage actor-critic on a GPU","author":"Babaeizadeh","year":"2017"},{"key":"mlstac9ae8bib70","article-title":"A framework for deep energy-based reinforcement learning with quantum speed-up","author":"Jerbi","year":"2019"},{"key":"mlstac9ae8bib71","doi-asserted-by":"publisher","DOI":"10.1038\/lsa.2017.146","article-title":"Twisted photons: new quantum perspectives in high dimensions","volume":"7","author":"Erhard","year":"2018","journal-title":"Light Sci. Appl."},{"key":"mlstac9ae8bib72","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.116.090405","article-title":"Automated search for new quantum experiments","volume":"116","author":"Krenn","year":"2016","journal-title":"Phys. Rev. Lett."},{"key":"mlstac9ae8bib73","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.118.080401","article-title":"Entanglement by path identity","volume":"118","author":"Krenn","year":"2017","journal-title":"Phys. Rev. Lett."},{"key":"mlstac9ae8bib74","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.119.240403","article-title":"Quantum experiments and graphs: multiparty states as coherent superpositions of perfect matchings","volume":"119","author":"Krenn","year":"2017","journal-title":"Phys. Rev. Lett."},{"key":"mlstac9ae8bib75","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0004-3702(98)00023-X","article-title":"Planning and acting in partially observable stochastic domains","volume":"101","author":"Kaelbling","year":"1998","journal-title":"Artif. Intell."},{"key":"mlstac9ae8bib76","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1007\/s42484-020-00023-9","article-title":"On the convergence of projective-simulation\u2013based reinforcement learning in Markov decision processes","volume":"2","author":"Boyajian","year":"2020","journal-title":"Quantum Mach. Intell."},{"key":"mlstac9ae8bib77","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2876494","article-title":"Benchmarking projective simulation in navigation problems","volume":"6","author":"Melnikov","year":"2018","journal-title":"IEEE Access"},{"key":"mlstac9ae8bib78","article-title":"Lectures on dynamics and relativity","author":"Tong","year":"2019"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac9ae8","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac9ae8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac9ae8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac9ae8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac9ae8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac9ae8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac9ae8\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac9ae8\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,19]],"date-time":"2022-12-19T10:31:48Z","timestamp":1671445908000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ac9ae8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":78,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,12,16]]},"published-print":{"date-parts":[[2022,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ac9ae8","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,1]]},"assertion":[{"value":"Operationally meaningful representations of physical systems in neural networks","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-07-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-10-17","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-12-16","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}