{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T18:08:13Z","timestamp":1787162893011,"version":"build-2736575974"},"reference-count":44,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T00:00:00Z","timestamp":1701043200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000266","name":"EPSRC","doi-asserted-by":"crossref","award":["EP\/W024101\/1"],"award-info":[{"award-number":["EP\/W024101\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"crossref","award":["725731"],"award-info":[{"award-number":["725731"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"crossref"}]},{"name":"U.S. Department of Energy, Office of Science, National Quantum Information Science Research Centers, Superconducting Quantum Materials and Systems Center","award":["DE-AC02-07CH11359"],"award-info":[{"award-number":["DE-AC02-07CH11359"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Adaptive gating plays a key role in temporal data processing via classical recurrent neural networks (RNNs), as it facilitates retention of past information necessary to predict the future, providing a mechanism that preserves invariance to time warping transformations. This paper builds on quantum RNNs (QRNNs), a dynamic model with quantum memory, to introduce a novel class of temporal data processing quantum models that preserve invariance to time-warping transformations of the (classical) input-output sequences. The model, referred to as\n                    <jats:italic>time warping-invariant QRNN (TWI-QRNN)<\/jats:italic>\n                    , augments a QRNN with a quantum\u2013classical adaptive gating mechanism that chooses whether to apply a parameterized unitary transformation at each time step as a function of the past samples of the input sequence via a classical recurrent model. The TWI-QRNN model class is derived from first principles, and its capacity to successfully implement time-warping transformations is experimentally demonstrated on examples with classical or quantum dynamics.\n                  <\/jats:p>","DOI":"10.1088\/2632-2153\/acff39","type":"journal-article","created":{"date-parts":[[2023,10,2]],"date-time":"2023-10-02T18:43:21Z","timestamp":1696272201000},"page":"045038","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Time-warping invariant quantum recurrent neural networks via quantum-classical adaptive gating"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0100-9344","authenticated-orcid":true,"given":"Ivana","family":"Nikoloska","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osvaldo","family":"Simeone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonardo","family":"Banchi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petar","family":"Veli\u010dkovi\u0107","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2023,11,27]]},"reference":[{"key":"mlstacff39bib1","first-page":"pp 603","article-title":"Natural language processing","author":"Chowdhary","year":"2020"},{"key":"mlstacff39bib2","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1126\/science.aaa8685","article-title":"Advances in natural language processing","volume":"349","author":"Hirschberg","year":"2015","journal-title":"Science"},{"key":"mlstacff39bib3","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1103\/RevModPhys.86.153","article-title":"Quantum simulation","volume":"86","author":"Georgescu","year":"2014","journal-title":"Rev. Mod. Phys."},{"key":"mlstacff39bib4","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.98.032309","article-title":"Quantum circuit learning","volume":"98","author":"Mitarai","year":"2018","journal-title":"Phys. Rev. A"},{"key":"mlstacff39bib5","first-page":"pp 37","article-title":"Long short-term memory","author":"Graves","year":"2012"},{"key":"mlstacff39bib6","first-page":"pp 6645","article-title":"Speech recognition with deep recurrent neural networks","author":"Graves","year":"2013"},{"key":"mlstacff39bib7","article-title":"Can recurrent neural networks warp time?","author":"Tallec","year":"2018"},{"key":"mlstacff39bib8","article-title":"Geometric deep learning: grids, groups, graphs, geodesics, and gauges","author":"Bronstein","year":"2021"},{"key":"mlstacff39bib9","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"mlstacff39bib10","first-page":"pp 1097","article-title":"Imagenet classification with deep convolutional neural networks","volume":"vol 25","author":"Krizhevsky","year":"2012"},{"key":"mlstacff39bib11","doi-asserted-by":"crossref","DOI":"10.1103\/PRXQuantum.3.030341","article-title":"Group-invariant quantum machine learning","author":"Larocca","year":"2022"},{"key":"mlstacff39bib12","article-title":"Exploiting symmetry in variational quantum machine learning","author":"Meyer","year":"2022"},{"key":"mlstacff39bib13","article-title":"Representation theory for geometric quantum machine learning","author":"Ragone","year":"2022"},{"key":"mlstacff39bib14","article-title":"Learning to learn with quantum neural networks via classical neural networks","author":"Verdon","year":"2019"},{"key":"mlstacff39bib15","article-title":"Quantum graph neural networks","author":"Verdon","year":"2019"},{"key":"mlstacff39bib16","article-title":"Decompositional quantum graph neural network","author":"Ai","year":"2022"},{"key":"mlstacff39bib17","first-page":"15401","article-title":"Equivariant quantum graph circuits","author":"Mernyei","year":"2022"},{"key":"mlstacff39bib18","article-title":"Theory for equivariant quantum neural networks","author":"Nguyen","year":"2022"},{"key":"mlstacff39bib19","article-title":"Theoretical guarantees for permutation-equivariant quantum neural networks","author":"Schatzki","year":"2022"},{"key":"mlstacff39bib20","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.11.041011","article-title":"Absence of barren plateaus in quantum convolutional neural networks","volume":"11","author":"Pesah","year":"2021","journal-title":"Phys. Rev. X"},{"key":"mlstacff39bib21","first-page":"pp 1368","article-title":"Recurrent quantum neural networks","volume":"vol 33","author":"Bausch","year":"2020"},{"key":"mlstacff39bib22","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.103.052414","article-title":"Learning temporal data with a variational quantum recurrent neural network","volume":"103","author":"Takaki","year":"2021","journal-title":"Phys. Rev. A"},{"key":"mlstacff39bib23","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.12.011007","article-title":"Quantum adaptive agents with efficient long-term memories","volume":"12","author":"Elliott","year":"2022","journal-title":"Phys. Rev. X"},{"key":"mlstacff39bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.125.260501","article-title":"Extreme dimensionality reduction with quantum modeling","volume":"125","author":"Elliott","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"mlstacff39bib25","article-title":"Provable superior accuracy in machine learned quantum models","author":"Yang","year":"2021"},{"key":"mlstacff39bib26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.14.024065","article-title":"Temporal information processing on noisy quantum computers","volume":"14","author":"Chen","year":"2020","journal-title":"Phys. Rev. Appl."},{"key":"mlstacff39bib27","article-title":"Reservoir computing via quantum recurrent neural networks","author":"Chen","year":"2022"},{"key":"mlstacff39bib28","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/aaf749","article-title":"Modelling non-Markovian quantum processes with recurrent neural networks","volume":"20","author":"Banchi","year":"2018","journal-title":"New J. Phys."},{"key":"mlstacff39bib29","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.128.180505","article-title":"Trainability of dissipative perceptron-based quantum neural networks","volume":"128","author":"Sharma","year":"2022","journal-title":"Phys. Rev. Lett."},{"key":"mlstacff39bib30","article-title":"Learning capability of parametrized quantum circuits","author":"Heimann","year":"2022"},{"key":"mlstacff39bib31","article-title":"Quantum neuron: an elementary building block for machine learning on quantum computers","author":"Cao","year":"2017"},{"key":"mlstacff39bib32","author":"Schuld","year":"2021"},{"key":"mlstacff39bib33","doi-asserted-by":"publisher","first-page":"386","DOI":"10.22331\/q-2021-01-25-386","article-title":"Measuring analytic gradients of general quantum evolution with the stochastic parameter shift rule","volume":"5","author":"Banchi","year":"2021","journal-title":"Quantum"},{"key":"mlstacff39bib34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.physrep.2022.01.001","article-title":"Quantum collision models: open system dynamics from repeated interactions","volume":"954","author":"Ciccarello","year":"2022","journal-title":"Phys. Rep."},{"key":"mlstacff39bib35","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/BF00992696","article-title":"Simple statistical gradient-following algorithms for connectionist reinforcement learning","volume":"8","author":"Williams","year":"1992","journal-title":"Mach. Learn."},{"key":"mlstacff39bib36","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1002\/sim.7080","article-title":"Pseudo maximum likelihood approach for the analysis of multivariate left-censored longitudinal data","volume":"36","author":"Solomon","year":"2017","journal-title":"Stat. Med."},{"key":"mlstacff39bib37","doi-asserted-by":"publisher","first-page":"1760","DOI":"10.1016\/j.cpc.2012.02.021","article-title":"Qutip: an open-source Python framework for the dynamics of open quantum systems","volume":"183","author":"Johansson","year":"2012","journal-title":"Comput. Phys. Commun."},{"key":"mlstacff39bib38","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: fundamental algorithms for scientific computing in Python","volume":"17","author":"(SciPy 1.0 Contributors)","year":"2020","journal-title":"Nat. Methods"},{"key":"mlstacff39bib39","article-title":"Quantum embeddings for machine learning","author":"Lloyd","year":"2020"},{"key":"mlstacff39bib40","doi-asserted-by":"publisher","first-page":"126","DOI":"10.1007\/s11128-019-2240-7","article-title":"Approximation of quantum control correction scheme using deep neural networks","volume":"18","author":"Ostaszewski","year":"2019","journal-title":"Quantum Inf. Process."},{"key":"mlstacff39bib41","first-page":"pp 591","article-title":"Taking gradients through experiments: LSTMs and memory proximal policy optimization for black-box quantum control","author":"August","year":"2018"},{"key":"mlstacff39bib42","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1126\/science.abn7293","article-title":"Quantum advantage in learning from experiments","volume":"376","author":"Huang","year":"2022","journal-title":"Science"},{"key":"mlstacff39bib43","author":"Meyn","year":"2022"},{"key":"mlstacff39bib44","author":"Peres","year":"1997"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acff39","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acff39\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acff39","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acff39\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acff39\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acff39\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acff39\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acff39\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T04:42:49Z","timestamp":1701060169000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acff39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,27]]},"references-count":44,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,11,27]]},"published-print":{"date-parts":[[2023,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/acff39","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,27]]},"assertion":[{"value":"Time-warping invariant quantum recurrent neural networks via quantum-classical adaptive gating","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 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-06-09","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-10-02","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-11-27","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}