{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T00:40:28Z","timestamp":1778632828947,"version":"3.51.4"},"reference-count":35,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T00:00:00Z","timestamp":1750896000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T00:00:00Z","timestamp":1750896000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000078","name":"Division of Materials Research","doi-asserted-by":"crossref","award":["DMR-2238360"],"award-info":[{"award-number":["DMR-2238360"]}],"id":[{"id":"10.13039\/100000078","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":[[2025,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Generative models aim to learn the probability distributions underlying data, enabling the generation of new, realistic samples. Quantum-inspired generative models, such as Born machines based on the matrix product state (MPS) framework, have demonstrated remarkable capabilities in unsupervised learning tasks. This study advances the Born machine paradigm by introducing trainable token embeddings through positive operator-valued measurements (POVMs), replacing the traditional approach of static tensor indices. Key technical innovations include encoding tokens as quantum measurement operators with trainable parameters and leveraging QR decomposition to adjust the physical dimensions of the MPS. This approach maximizes the utilization of operator space and enhances the model\u2019s expressiveness. Empirical results on RNA data demonstrate that the proposed method significantly reduces negative log-likelihood compared to one-hot embeddings, with higher physical dimensions further enhancing single-site probabilities and multi-site correlations. The model also outperforms GPT-2 in single-site estimation and achieves competitive correlation modeling, showcasing the potential of trainable POVM embeddings for complex data correlations in quantum-inspired sequence modeling.<\/jats:p>","DOI":"10.1088\/2632-2153\/adde29","type":"journal-article","created":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T22:58:23Z","timestamp":1748473103000},"page":"025071","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Sequential learning on a tensor network Born machine with trainable token embedding"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7665-6415","authenticated-orcid":true,"given":"Wanda","family":"Hou","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Miao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4080-5340","authenticated-orcid":true,"given":"Yi-Zhuang","family":"You","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,6,26]]},"reference":[{"key":"mlstadde29bib1","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"LeCun","year":"2015","journal-title":"Nature"},{"key":"mlstadde29bib2","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.91.045002","volume":"91","author":"Carleo","year":"2019","journal-title":"Rev. Mod. Phys."},{"key":"mlstadde29bib3","author":"Kingma","year":"2013"},{"key":"mlstadde29bib4","author":"Goodfellow","year":"2014"},{"key":"mlstadde29bib5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.98.012324","volume":"98","author":"Dallaire-Demers","year":"2018","journal-title":"Phys. Rev. A"},{"key":"mlstadde29bib6","author":"Vaswani","year":"2017"},{"key":"mlstadde29bib7","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/S0364-0213(85)80012-4","volume":"9","author":"Ackley","year":"1985","journal-title":"Cogn. Sci."},{"key":"mlstadde29bib8","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1146\/annurev-statistics-010814-020120","volume":"2","author":"Salakhutdinov","year":"2015","journal-title":"Annu. Rev. Stat. Appl."},{"key":"mlstadde29bib9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.8.031012","volume":"8","author":"Han","year":"2018","journal-title":"Phys. Rev. X"},{"key":"mlstadde29bib10","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.106.022612","volume":"106","author":"Kiss","year":"2022","journal-title":"Phys. Rev. A"},{"key":"mlstadde29bib11","author":"McClain Gomez","year":"2021"},{"key":"mlstadde29bib12","doi-asserted-by":"publisher","first-page":"138","DOI":"10.3389\/fpsyg.2012.00138","volume":"3","author":"Trueblood","year":"2012","journal-title":"Front. Psychol."},{"key":"mlstadde29bib13","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2015.0233","volume":"374","author":"Khrennikov","year":"2016","journal-title":"Phil. Trans. R. Soc. A"},{"key":"mlstadde29bib14","doi-asserted-by":"publisher","first-page":"583","DOI":"10.3390\/e20080583","volume":"20","author":"Cheng","year":"2018","journal-title":"Entropy"},{"key":"mlstadde29bib15","author":"Liu","year":"2018"},{"key":"mlstadde29bib16","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1038\/s42254-019-0086-7","volume":"1","author":"Or\u00fas","year":"2019","journal-title":"Nat. Rev. Phys."},{"key":"mlstadde29bib17","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.9.031041","volume":"9","author":"Liao","year":"2019","journal-title":"Phys. Rev. X"},{"key":"mlstadde29bib18","author":"Liu","year":"2021"},{"key":"mlstadde29bib19","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.98.032309","volume":"98","author":"Mitarai","year":"2018","journal-title":"Phys. Rev. A"},{"key":"mlstadde29bib20","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2022.126907","volume":"593","author":"Gong","year":"2022","journal-title":"Physica A"},{"key":"mlstadde29bib21","author":"Ma","year":"2019"},{"key":"mlstadde29bib22","author":"Glos","year":"2022"},{"key":"mlstadde29bib23","author":"Zambrini Cruzeiro","year":"2023"},{"key":"mlstadde29bib24","doi-asserted-by":"publisher","DOI":"10.1103\/PRXQuantum.2.040342","volume":"2","author":"Garc\u00eda-P\u00e9rez","year":"2021","journal-title":"PRX Quantum"},{"key":"mlstadde29bib25","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/s10107-012-0584-1","volume":"142","author":"Wen","year":"2013","journal-title":"Math. Program."},{"key":"mlstadde29bib26","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac48a2","volume":"3","author":"Geng","year":"2022","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstadde29bib27","doi-asserted-by":"publisher","first-page":"D180","DOI":"10.1093\/nar\/gkv1081","volume":"44","author":"Szymanski","year":"2016","journal-title":"Nucl. Acids Res."},{"key":"mlstadde29bib28","doi-asserted-by":"publisher","first-page":"5800","DOI":"10.1038\/s41467-021-25756-4","volume":"12","author":"Trinquier","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstadde29bib29","author":"Hugging Face GPT-2 model","year":"2023"},{"key":"mlstadde29bib30","article-title":"Github repository","author":"Wanda Hou","year":"2023"},{"key":"mlstadde29bib31","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevX.12.011047","volume":"12","author":"Haghshenas","year":"2022","journal-title":"Phys. Rev. X"},{"key":"mlstadde29bib32","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/ad04e6","volume":"9","author":"Rudolph","year":"2024","journal-title":"Quantum Sci. Technol."},{"key":"mlstadde29bib33","first-page":"81","article-title":"Lecture notes for physics 229: quantum information and computation","author":"Preskill","year":"1998"},{"key":"mlstadde29bib34","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevA.98.062324","volume":"98","author":"Liu","year":"2018","journal-title":"Phys. Rev. A"},{"key":"mlstadde29bib35","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1038\/s41534-019-0157-8","volume":"5","author":"Benedetti","year":"2019","journal-title":"npj Quantum Inf."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adde29","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adde29\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adde29","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adde29\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adde29\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adde29\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adde29\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adde29\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T13:31:48Z","timestamp":1750944708000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adde29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,26]]},"references-count":35,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,6,26]]},"published-print":{"date-parts":[[2025,6,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/adde29","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,26]]},"assertion":[{"value":"Sequential learning on a tensor network Born machine with trainable token embedding","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 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2025-01-22","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-05-28","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-06-26","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}