{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T18:25:54Z","timestamp":1743013554601,"version":"3.37.3"},"reference-count":51,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:00:00Z","timestamp":1707955200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T00:00:00Z","timestamp":1707955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Despite their promise to facilitate new scientific discoveries, the opaqueness of neural networks presents a challenge in interpreting the logic behind their findings. Here, we use a eXplainable-AI technique called <jats:italic>inception<\/jats:italic> or <jats:italic>deep dreaming<\/jats:italic>, which has been invented in machine learning for computer vision. We use this technique to explore what neural networks learn about quantum optics experiments. Our story begins by training deep neural networks on the properties of quantum systems. Once trained, we \u2018invert\u2019 the neural network\u2014effectively asking how it imagines a quantum system with a specific property, and how it would continuously modify the quantum system to change a property. We find that the network can shift the initial distribution of properties of the quantum system, and we can conceptualize the learned strategies of the neural network. Interestingly, we find that, in the first layers, the neural network identifies simple properties, while in the deeper ones, it can identify complex quantum structures and even quantum entanglement. This is in reminiscence of long-understood properties known in computer vision, which we now identify in a complex natural science task. Our approach could be useful in a more interpretable way to develop new advanced AI-based scientific discovery techniques in quantum physics.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad2628","type":"journal-article","created":{"date-parts":[[2024,2,5]],"date-time":"2024-02-05T22:22:45Z","timestamp":1707171765000},"page":"015029","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep quantum graph dreaming: deciphering neural network insights into quantum experiments"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5661-2403","authenticated-orcid":true,"given":"Tareq","family":"Jaouni","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00f6ren","family":"Arlt","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0545-360X","authenticated-orcid":true,"given":"Carlos","family":"Ruiz-Gonzalez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8168-7304","authenticated-orcid":true,"given":"Ebrahim","family":"Karimi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuemei","family":"Gu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mario","family":"Krenn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,2,15]]},"reference":[{"year":"2022","author":"Dawid","article-title":"Modern applications of machine learning in quantum sciences","key":"mlstad2628bib1"},{"key":"mlstad2628bib2","doi-asserted-by":"publisher","DOI":"10.1103\/physreva.107.010101","article-title":"Artificial intelligence and machine learning for quantum technologies","volume":"107","author":"Krenn","year":"2023","journal-title":"Phys. Rev. A"},{"key":"mlstad2628bib3","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":"mlstad2628bib4","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1038\/s42254-022-00518-3","article-title":"On scientific understanding with artificial intelligence","volume":"4","author":"Krenn","year":"2022","journal-title":"Nat. Rev. Phys."},{"year":"2017","author":"Doran","key":"mlstad2628bib5"},{"key":"mlstad2628bib6","doi-asserted-by":"publisher","first-page":"4793","DOI":"10.1109\/TNNLS.2020.3027314","article-title":"A survey on explainable artificial intelligence (XAI):towards medical XAI","volume":"32","author":"Tjoa","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"mlstad2628bib7","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1613\/jair.1.12228","article-title":"A survey on the explainability of supervised machine learning","volume":"70","author":"Burkart","year":"2021","journal-title":"J. Artif. Intell. Res."},{"year":"2017","author":"Samek","article-title":"Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models","key":"mlstad2628bib8"},{"key":"mlstad2628bib9","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":"mlstad2628bib10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.033499","article-title":"Discovering symmetry invariants and conserved quantities by interpreting siamese neural networks","volume":"2","author":"Wetzel","year":"2020","journal-title":"Phys. Rev. Res."},{"key":"mlstad2628bib11","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac338d","article-title":"Hessian-based toolbox for reliable and interpretable machine learning in physics","volume":"3","author":"Dawid","year":"2021","journal-title":"Mach. Learn. Sci. Technol."},{"key":"mlstad2628bib12","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/abc463","article-title":"Phase detection with neural networks: interpreting the black box","volume":"22","author":"Dawid","year":"2020","journal-title":"New J. Phys."},{"key":"mlstad2628bib13","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abffe7","article-title":"Unsupervised machine learning of topological phase transitions from experimental data","volume":"2","author":"K\u00e4ming","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad2628bib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.96.184410","article-title":"Machine learning of explicit order parameters: from the ising model to su(2) lattice gauge theory","volume":"96","author":"Wetzel","year":"2017","journal-title":"Phys. Rev. B"},{"key":"mlstad2628bib15","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1038\/s41534-018-0077-z","article-title":"Learning hard quantum distributions with variational autoencoders","volume":"4","author":"Rocchetto","year":"2018","journal-title":"npj Quantum Inf."},{"key":"mlstad2628bib16","doi-asserted-by":"publisher","first-page":"544","DOI":"10.1038\/s42256-022-00493-5","article-title":"Learning interpretable representations of entanglement in quantum optics experiments using deep generative models","volume":"4","author":"Flam-Shepherd","year":"2022","journal-title":"Nat. Mach. Intell."},{"key":"mlstad2628bib17","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad16a0","article-title":"Explainable representation learning of small quantum states","volume":"5","author":"Frohnert","year":"2024","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad2628bib18","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1038\/s42254-020-0230-4","article-title":"Computer-inspired quantum experiments","volume":"2","author":"Krenn","year":"2020","journal-title":"Nat. Rev. Phys."},{"key":"mlstad2628bib19","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":"mlstad2628bib20","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ab4d89","article-title":"Designing quantum experiments with a genetic algorithm","volume":"4","author":"Nichols","year":"2019","journal-title":"Quantum Sci. Technol."},{"key":"mlstad2628bib21","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/s42484-019-00003-8","article-title":"A hybrid machine learning algorithm for designing quantum experiments","volume":"1","author":"O\u2019Driscoll","year":"2019","journal-title":"Quantum Mach. Intell."},{"key":"mlstad2628bib22","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.107.062607","article-title":"Automated design of quantum-optical experiments for device-independent quantum key distribution","volume":"107","author":"Valcarce","year":"2023","journal-title":"Phys. Rev. A"},{"key":"mlstad2628bib23","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/aaf59e","article-title":"Machine learning method for state preparation and gate synthesis on photonic quantum computers","volume":"4","author":"Arrazola","year":"2019","journal-title":"Quantum Sci. Technol."},{"key":"mlstad2628bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.11.031044","article-title":"Conceptual understanding through efficient automated design of quantum optical experiments","volume":"11","author":"Krenn","year":"2021","journal-title":"Phys. Rev. X"},{"key":"mlstad2628bib25","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.22331\/q-2023-12-12-1204","article-title":"Digital discovery of 100 diverse quantum experiments with PyTheus","volume":"7","author":"Ruiz-Gonzalez","year":"2023","journal-title":"Quantum"},{"key":"mlstad2628bib26","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":"mlstad2628bib27","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.125.050501","article-title":"Computer-inspired concept for high-dimensional multipartite quantum gates","volume":"125","author":"Gao","year":"2020","journal-title":"Phys. Rev. Lett."},{"year":"2022","author":"Arlt","article-title":"Digital discovery of a scientific concept at the core of experimental quantum optics","key":"mlstad2628bib28"},{"key":"mlstad2628bib29","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1364\/OPTICAQ.502451","article-title":"Experimental solutions to the high-dimensional mean king\u2019s problem","volume":"1","author":"Jaouni","year":"2023","journal-title":"Opt. Quantum"},{"year":"2015","author":"Mordvintsev","article-title":"Inceptionism: going deeper into neural networks","key":"mlstad2628bib30"},{"year":"2022","author":"Lifshitz","article-title":"Quantum deep dreaming: a novel approach for quantum circuit design","key":"mlstad2628bib31"},{"key":"mlstad2628bib32","doi-asserted-by":"publisher","first-page":"03LT02","DOI":"10.1088\/2632-2153\/ac09d6","article-title":"Deep molecular dreaming: inverse machine learning for de-novo molecular design and interpretability with surjective representations","volume":"2","author":"Shen","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad2628bib33","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.95.245134","article-title":"Probing many-body localization with neural networks","volume":"95","author":"Schindler","year":"2017","journal-title":"Phys. Rev. B"},{"key":"mlstad2628bib34","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1038\/s41567-020-1018-2","article-title":"Machine learning the thermodynamic arrow of time","volume":"17","author":"Seif","year":"2021","journal-title":"Nat. Phys."},{"key":"mlstad2628bib35","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":"2017b","journal-title":"Phys. Rev. Lett."},{"key":"mlstad2628bib36","doi-asserted-by":"publisher","first-page":"4147","DOI":"10.1073\/pnas.1815884116","article-title":"Quantum experiments and graphs II: quantum interference, computation and state generation","volume":"116","author":"Gu","year":"2019a"},{"key":"mlstad2628bib37","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.99.032338","article-title":"Quantum experiments and graphs. III. High-dimensional and multiparticle entanglement","volume":"99","author":"Gu","year":"2019b","journal-title":"Phys. Rev. A"},{"key":"mlstad2628bib38","first-page":"p W4C.6","article-title":"Integrated quantum photonics on silicon platform","author":"Ding","year":"2020"},{"key":"mlstad2628bib39","doi-asserted-by":"publisher","DOI":"10.1002\/qute.201900058","article-title":"Progress on integrated quantum photonic sources with silicon","volume":"3","author":"Feng","year":"2020","journal-title":"Adv. Quantum Technol."},{"key":"mlstad2628bib40","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1038\/s42254-021-00398-z","article-title":"The potential and global outlook of integrated photonics for quantum technologies","volume":"4","author":"Pelucchi","year":"2022","journal-title":"Nat. Rev. Phys."},{"key":"mlstad2628bib41","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.22331\/q-2023-12-12-1204","article-title":"Very-large-scale integrated quantum graph photonics","volume":"1","author":"Bao","year":"2023","journal-title":"Nat. Photon."},{"key":"mlstad2628bib42","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1038\/s41467-023-37228-y","article-title":"Multiphoton non-local quantum interference controlled by an undetected photon","volume":"14","author":"Qian","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstad2628bib43","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1364\/OPTICA.474750","article-title":"On-chip quantum interference between the origins of a multi-photon state","volume":"10","author":"Feng","year":"2023","journal-title":"Optica"},{"key":"mlstad2628bib44","first-page":"pp 69","article-title":"Going beyond bell\u2019s theorem","author":"Greenberger","year":"1989"},{"key":"mlstad2628bib45","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.65.032108","article-title":"Bell\u2019s theorem with and without inequalities for the three-qubit Greenberger-Horne-Zeilinger and W states","volume":"65","author":"Cabello","year":"2002","journal-title":"Phys. Rev. A"},{"key":"mlstad2628bib46","first-page":"27","article-title":"Entanglement of formation and concurrence","volume":"1","author":"Wootters","year":"2001","journal-title":"Quantum Inf. Comput."},{"year":"2016","author":"Nguyen","article-title":"Multifaceted feature visualization: uncovering the different types of features learned by each neuron in deep neural networks","key":"mlstad2628bib47"},{"year":"2013","author":"Simonyan","article-title":"Deep inside convolutional networks: visualising image classification models and saliency maps","key":"mlstad2628bib48"},{"key":"mlstad2628bib49","first-page":"pp 8867","article-title":"Equivariant diffusion for molecule generation in 3d","author":"Hoogeboom","year":"2022"},{"key":"mlstad2628bib50","article-title":"Pytorch: an imperative style, high-performance deep learning library","volume":"vol 32","author":"Paszke","year":"2019"},{"year":"2014","author":"Kingma","article-title":"Adam: a method for stochastic optimization","key":"mlstad2628bib51"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2628","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2628\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2628","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2628\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2628\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2628\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2628\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2628\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,15]],"date-time":"2024-02-15T07:19:00Z","timestamp":1707981540000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad2628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,15]]},"references-count":51,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,2,15]]},"published-print":{"date-parts":[[2024,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad2628","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2024,2,15]]},"assertion":[{"value":"Deep quantum graph dreaming: deciphering neural network insights into quantum experiments","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 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-10-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-01-31","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-02-15","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}