{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T18:08:28Z","timestamp":1774721308886,"version":"3.50.1"},"reference-count":38,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T00:00:00Z","timestamp":1765324800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"MUR Dipartimenti di Eccellenza","award":["2023-2027"],"award-info":[{"award-number":["2023-2027"]}]},{"DOI":"10.13039\/100023048","name":"ICSC","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100023048","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Centro Nazionale di Ricerca in High Performance Computing, Big Data and Quantum Computing"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Tensor networks (TNs) are a computational paradigm used for representing quantum many-body systems. Recent works have shown how TNs can also be applied to perform machine learning (ML) tasks, yielding comparable results to standard supervised learning techniques. In this work, we study the use of Tree TNs (TTNs) in high-frequency real-time applications by exploiting the low-latency hardware of the field-programmable gate array (FPGA) technology. We present different implementations of TTN classifiers, capable of performing inference on classical ML datasets as well as on complex physics data. A preparatory analysis of bond dimensions and weight quantization is realized in the training phase, together with entanglement entropy and correlation measurements, that help setting the choice of the TTN architecture. The generated TTNs are then deployed on a hardware accelerator; using an FPGA integrated into a server, the inference of the TTN is completely offloaded. Eventually, a classifier for high energy physics applications is implemented and executed fully pipelined with sub-microsecond latency.<\/jats:p>","DOI":"10.1088\/2632-2153\/ae25b5","type":"journal-article","created":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T11:19:52Z","timestamp":1765365592000},"page":"045062","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Ultra-low latency quantum-inspired machine learning predictors implemented on FPGA"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0689-5090","authenticated-orcid":true,"given":"Lorenzo","family":"Borella","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9531-1371","authenticated-orcid":true,"given":"Alberto","family":"Coppi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5140-9154","authenticated-orcid":true,"given":"Andrea","family":"Triossi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1118-6205","authenticated-orcid":false,"given":"Jacopo","family":"Pazzini","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4281-4582","authenticated-orcid":false,"given":"Marco","family":"Zanetti","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8442-9055","authenticated-orcid":true,"given":"Andrea","family":"Stanco","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7494-8202","authenticated-orcid":true,"given":"Marco","family":"Trenti","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,12,10]]},"reference":[{"key":"mlstae25b5bib1","doi-asserted-by":"publisher","first-page":"964","DOI":"10.22331\/q-2023-03-30-964","type":"journal-article","article-title":"Simulating quantum circuits using tree tensor networks","volume":"7","author":"Seitz","year":"2023","journal-title":"Quantum"},{"key":"mlstae25b5bib2","doi-asserted-by":"publisher","first-page":"578","DOI":"10.1038\/s43588-021-00119-7","type":"journal-article","article-title":"Efficient parallelization of tensor network contraction for simulating quantum computation","volume":"1","author":"Huang","year":"2021","journal-title":"Nat. Comput. Sci."},{"key":"mlstae25b5bib3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.5.013031","type":"journal-article","article-title":"Automatic structural optimization of tree tensor networks","volume":"5","author":"Hikihara","year":"2023","journal-title":"Phys. Rev. Res."},{"key":"mlstae25b5bib4","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1007\/s10955-011-0237-4","type":"journal-article","article-title":"Tensor network states and geometry","volume":"145","author":"Evenbly","year":"2011","journal-title":"J. Stat. Phys."},{"key":"mlstae25b5bib5","article-title":"Machine learning with tree tensor networks, CP rank constraints, and tensor dropout","author":"Hao","year":"2023","type":"preprint"},{"key":"mlstae25b5bib6","article-title":"Tensor networks meet neural networks: a survey and future perspectives","author":"Wang","year":"2023","type":"preprint"},{"key":"mlstae25b5bib7","doi-asserted-by":"crossref","DOI":"10.4171\/mag\/101","type":"preprint","article-title":"Tensor networks in machine learning","author":"Sengupta","year":"2022"},{"key":"mlstae25b5bib8","doi-asserted-by":"publisher","first-page":"023A02","DOI":"10.1093\/ptep\/ptad018","type":"journal-article","article-title":"Entanglement bipartitioning and tree tensor networks","volume":"2023","author":"Okunishi","year":"2023","journal-title":"Prog. Theor. Exp. Phys."},{"key":"mlstae25b5bib9","doi-asserted-by":"publisher","DOI":"10.1088\/1748-0221\/13\/07\/P07027","type":"journal-article","article-title":"Fast inference of deep neural networks in FPGAs for particle physics","volume":"13","author":"Duarte","year":"2018","journal-title":"J. Instrum."},{"key":"mlstae25b5bib10","article-title":"Field-programmable gate array architecture for deep learning: survey & future directions","author":"Boutros","year":"2024","type":"preprint"},{"key":"mlstae25b5bib11","author":"Levental","type":"preprint"},{"key":"mlstae25b5bib12","author":"Iris Dataset","year":"2016","type":"other"},{"key":"mlstae25b5bib13","author":"Titanic Dataset","year":"2025","type":"other"},{"key":"mlstae25b5bib14","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/s41534-021-00443-w","type":"journal-article","article-title":"Quantum-inspired machine learning on high-energy physics data","volume":"7","author":"Felser","year":"2021","journal-title":"npj Quantum Inf."},{"key":"mlstae25b5bib15","doi-asserted-by":"publisher","DOI":"10.7483\/OPENDATA.LHCB.N75T.TJPE","type":"other","article-title":"Simulated jet samples for quark flavour identification studies","author":"LHCb collaboration","year":"2020"},{"key":"mlstae25b5bib16","article-title":"Supervised learning with tensor networks","author":"Stoudenmire","year":"2016","type":"conference-proceedings"},{"key":"mlstae25b5bib17","article-title":"Tensornetwork for machine learning","author":"Efthymiou","year":"2019","type":"preprint"},{"key":"mlstae25b5bib18","doi-asserted-by":"crossref","DOI":"10.26421\/QIC7.5-6-1","type":"preprint","article-title":"Matrix product state representations","author":"Perez-Garcia","year":"2007"},{"key":"mlstae25b5bib19","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1103\/PhysRevA.74.022320","type":"journal-article","volume":"74","author":"Shi","year":"2006","journal-title":"Phys. Rev. A"},{"key":"mlstae25b5bib20","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/aaba1a","type":"journal-article","article-title":"Learning relevant features of data with multi-scale tensor networks","volume":"3","author":"Stoudenmire","year":"2018","journal-title":"Quantum Sci. Technol."},{"key":"mlstae25b5bib21","doi-asserted-by":"publisher","DOI":"10.1109\/HISTELCON47851.2019.9040130","type":"conference-proceedings","article-title":"The evolution of digital signal processors","author":"Ibrahim","year":"2019"},{"key":"mlstae25b5bib22","author":"Advanced Micro Devices, Inc. (n.d.)","type":"other"},{"key":"mlstae25b5bib23","article-title":"UltraScale FPGA product tables and product selection guide","author":"AMD","year":"2016","type":"other"},{"key":"mlstae25b5bib24","author":"AMD Xilinx","year":"2018","type":"other"},{"key":"mlstae25b5bib25","doi-asserted-by":"publisher","DOI":"10.4108\/eai.24-3-2022.2319063","type":"other","article-title":"Classification of Iris dataset using bayesian models","author":"Sharma","year":"2023"},{"key":"mlstae25b5bib26","doi-asserted-by":"publisher","first-page":"1959","DOI":"10.11591\/ijece.v14i2.pp1959-1968","type":"journal-article","article-title":"Comparison of Iris dataset classification with Gaussian na\u00efve Bayes and decision tree algorithms","volume":"14","author":"Dani","year":"2024","journal-title":"Int. J. Electr. Comput. Eng. (IJECE)"},{"key":"mlstae25b5bib27","doi-asserted-by":"publisher","DOI":"10.54097\/hset.v23i.3620","type":"conference-proceedings","article-title":"Study for iris classification based on multiple machine learning models","author":"Zhou","year":"2023"},{"key":"mlstae25b5bib28","article-title":"Titanic survival prediction using machine learning","author":"GeeksforGeeks","year":"2023","type":"other"},{"key":"mlstae25b5bib29","article-title":"Titanic dataset machine learning tutorial","author":"Arrikto Academy","year":"2023","type":"other"},{"key":"mlstae25b5bib30","doi-asserted-by":"publisher","first-page":"JHE08(2022)014","DOI":"10.1007\/JHEP08(2022)014","type":"journal-article","article-title":"Quantum machine learning for b-jet charge identification","author":"Gianelle","year":"2022","journal-title":"J. High Energy Phys."},{"key":"mlstae25b5bib31","article-title":"Automating quantum feature map design via large language models","author":"Sakka","year":"2025","type":"preprint"},{"key":"mlstae25b5bib32","article-title":"Computer engineering education","author":"Real Digital","year":"2024","type":"other"},{"key":"mlstae25b5bib33","author":"AMD","year":"2024","type":"other"},{"key":"mlstae25b5bib34","doi-asserted-by":"publisher","first-page":"2657","DOI":"10.1140\/epjs\/s11734-024-01234-y","type":"journal-article","article-title":"Machine learning in high energy physics: a review of heavy-flavor jet tagging at the LHC","volume":"233","author":"Mondal","year":"2024","journal-title":"Eur. Phys. J. Spec. Top."},{"key":"mlstae25b5bib35","doi-asserted-by":"publisher","DOI":"10.3390\/app122010574","type":"journal-article","article-title":"Machine learning applications for jet tagging in the CMS experiment","volume":"12","author":"Cagnotta","year":"2022","journal-title":"Appl. Sci."},{"key":"mlstae25b5bib36","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac0ea1","type":"journal-article","article-title":"Fast convolutional neural networks on FPGAs with HLS4ML","volume":"2","author":"Aarrestad","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstae25b5bib37","article-title":"Ultra fast transformers on fpgas for particle physics experiments","author":"Jiang","year":"2024","type":"preprint"},{"key":"mlstae25b5bib38","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ad5f10","type":"journal-article","article-title":"Ultrafast jet classification at the HL-LHCMach","volume":"5","author":"Patrick","year":"2024","journal-title":"Learn.: Sci. Technol."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae25b5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae25b5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae25b5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae25b5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T11:19:55Z","timestamp":1765365595000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ae25b5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,10]]},"references-count":38,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12,10]]},"published-print":{"date-parts":[[2025,12,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ae25b5","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,10]]},"assertion":[{"value":"Ultra-low latency quantum-inspired machine learning predictors implemented on FPGA","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":"2025-09-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-11-28","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-12-10","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}