{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T15:45:54Z","timestamp":1759160754964,"version":"3.37.3"},"reference-count":65,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T00:00:00Z","timestamp":1717632000000},"content-version":"vor","delay-in-days":5,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T00:00:00Z","timestamp":1717632000000},"content-version":"tdm","delay-in-days":5,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100004359","name":"Vetenskapsr\u00e5det","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100010785","name":"Canada First Research Excellence Fund","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100010785","id-type":"DOI","asserted-by":"crossref"}]},{"name":"prothe Swedish National Strategic e-Science program eSSENCE"},{"name":"Swedish National Infrastructure for Computing"},{"DOI":"10.13039\/100007631","name":"Canadian Institute for Advanced Research","doi-asserted-by":"crossref","award":["Ed Clark Chair of Advanced Materials"],"award-info":[{"award-number":["Ed Clark Chair of Advanced Materials"]}],"id":[{"id":"10.13039\/100007631","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"crossref","award":["772834"],"award-info":[{"award-number":["772834"]}],"id":[{"id":"10.13039\/100010663","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":[[2024,6,1]]},"abstract":"Abstract<\/jats:title>\n For many machine learning applications in science, data acquisition, not training, is the bottleneck even when avoiding experiments and relying on computation and simulation. Correspondingly, and in order to reduce cost and carbon footprint, training data efficiency is key. We introduce minimal multilevel machine learning (M3L) which optimizes training data set sizes using a loss function at multiple levels of reference data in order to minimize a combination of prediction error with overall training data acquisition costs (as measured by computational wall-times). Numerical evidence has been obtained for calculated atomization energies and electron affinities of thousands of organic molecules at various levels of theory including HF, MP2, DLPNO-CCSD(T), DFHFCABS, PNOMP2F12, and PNOCCSD(T)F12, and treating them with basis sets TZ, cc-pVTZ, and AVTZ-F12. Our M3L benchmarks for reaching chemical accuracy in distinct chemical compound sub-spaces indicate substantial computational cost reductions by factors of \u223c1.01, 1.1, 3.8, 13.8, and 25.8 when compared to heuristic sub-optimal multilevel machine learning (M2L) for the data sets QM7b, QM9\n \n \n \n \n \n \n LCCSD<\/mml:mi>\n (<\/mml:mo>\n T<\/mml:mi>\n )<\/mml:mo>\n <\/mml:mrow>\n <\/mml:msup>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>, Electrolyte Genome Project, QM9\n \n \n \n \n \n \n AE<\/mml:mi>\n <\/mml:mrow>\n \n CCSD<\/mml:mi>\n (<\/mml:mo>\n T<\/mml:mi>\n )<\/mml:mo>\n <\/mml:mrow>\n <\/mml:msubsup>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>, and QM9\n \n \n \n \n \n \n EA<\/mml:mi>\n <\/mml:mrow>\n \n CCSD<\/mml:mi>\n (<\/mml:mo>\n T<\/mml:mi>\n )<\/mml:mo>\n <\/mml:mrow>\n <\/mml:msubsup>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>, respectively. Furthermore, we use M2L to investigate the performance for 76 density functionals when used within multilevel learning and building on the following levels drawn from the hierarchy of Jacobs Ladder: LDA, GGA, mGGA, and hybrid functionals. Within M2L and the molecules considered, mGGAs do not provide any noticeable advantage over GGAs. Among the functionals considered and in combination with LDA, the three on average top performing GGA and Hybrid levels for atomization energies on QM9 using M3L correspond respectively to PW91, KT2, B97D, and \u03c4<\/jats:italic>-HCTH, B3LYP\n \n \n \n \u2217<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math>\n <\/jats:inline-formula>(VWN5), and TPSSH.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad4ae5","type":"journal-article","created":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T23:03:35Z","timestamp":1715641415000},"page":"025058","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":14,"title":["Reducing training data needs with minimal multilevel machine learning (M3L)"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9382-2342","authenticated-orcid":true,"given":"Stefan","family":"Heinen","sequence":"first","affiliation":[]},{"given":"Danish","family":"Khan","sequence":"additional","affiliation":[]},{"given":"Guido","family":"Falk von Rudorff","sequence":"additional","affiliation":[]},{"given":"Konstantin","family":"Karandashev","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Jose Arismendi Arrieta","sequence":"additional","affiliation":[]},{"given":"Alastair J A","family":"Price","sequence":"additional","affiliation":[]},{"given":"Surajit","family":"Nandi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3198-5116","authenticated-orcid":true,"given":"Arghya","family":"Bhowmik","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2352-0458","authenticated-orcid":true,"given":"Kersti","family":"Hermansson","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7419-0466","authenticated-orcid":true,"given":"O","family":"Anatole von Lilienfeld","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,6,6]]},"reference":[{"key":"mlstad4ae5bib1","doi-asserted-by":"publisher","DOI":"10.1103\/physrevlett.108.058301","article-title":"Fast and accurate modeling of molecular atomization energies with machine learning","volume":"108","author":"Rupp","year":"2012","journal-title":"Phys. Rev. Lett."},{"key":"mlstad4ae5bib2","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.bdr.2015.04.001","article-title":"Efficient machine learning for big data: a review","volume":"2","author":"Al-Jarrah","year":"2015","journal-title":"Big Data Res."},{"key":"mlstad4ae5bib3","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ab6ac4","article-title":"Machine learning the computational cost of quantum chemistry","volume":"1","author":"Heinen","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad4ae5bib4","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1016\/j.ensm.2020.06.033","article-title":"Machine learning assisted materials design and discovery for rechargeable batteries","volume":"31","author":"Liu","year":"2020","journal-title":"Energy Storage Mater."},{"key":"mlstad4ae5bib5","doi-asserted-by":"publisher","first-page":"2331","DOI":"10.1021\/acs.jctc.9b00057","article-title":"Learning from failure: predicting electronic structure calculation outcomes with machine learning models","volume":"15","author":"Duan","year":"2019","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad4ae5bib6","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1021\/acs.jpca.9b08723","article-title":"Performance and cost assessment of machine learning interatomic potentials","volume":"124","author":"Zuo","year":"2020","journal-title":"J. Phys. Chem. A"},{"key":"mlstad4ae5bib7","doi-asserted-by":"publisher","DOI":"10.1016\/j.matre.2021.100047","article-title":"Computational discovery of energy materials in the era of big data and machine learning: a critical review","volume":"1","author":"Lu","year":"2021","journal-title":"Mater. Rep.: Energy"},{"key":"mlstad4ae5bib8","doi-asserted-by":"publisher","DOI":"10.1063\/5.0055522","article-title":"Software for the frontiers of quantum chemistry: an overview of developments in the Q-Chem 5 package","volume":"155","author":"Epifanovsky","year":"2021","journal-title":"J. Chem. Phys."},{"key":"mlstad4ae5bib9","doi-asserted-by":"publisher","first-page":"7447","DOI":"10.1021\/acs.jctc.1c00562","article-title":"Inq, a modern GPU-accelerated computational framework for (time-dependent) density functional theory","volume":"17","author":"Andrade","year":"2021","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad4ae5bib10","doi-asserted-by":"crossref","DOI":"10.1063\/5.0152215","article-title":"Kernel based quantum machine learning at record rate : many-body distribution functionals as compact representations","author":"Khan","year":"2023"},{"key":"mlstad4ae5bib11","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1038\/s41557-020-0527-z","article-title":"Quantum machine learning using atom-in-molecule-based fragments selected on the fly","volume":"12","author":"Huang","year":"2020","journal-title":"Nat. Chem."},{"key":"mlstad4ae5bib12","doi-asserted-by":"publisher","DOI":"10.1063\/1.5020710","article-title":"Alchemical and structural distribution based representation for universal quantum machine learning","volume":"148","author":"Faber","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstad4ae5bib13","doi-asserted-by":"publisher","DOI":"10.1063\/1.5126701","article-title":"Fchl revisited: faster and more accurate quantum machine learning","volume":"152","author":"Christensen","year":"2020","journal-title":"J. Chem. Phys."},{"key":"mlstad4ae5bib14","doi-asserted-by":"publisher","DOI":"10.1039\/C8CP05921G","article-title":"Feature optimization for atomistic machine learning yields a data-driven construction of the periodic table of the elements","volume":"20","author":"Willatt","year":"2018","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstad4ae5bib15","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1021\/acs.jctc.8b00908","article-title":"SchNetPack: a deep learning toolbox for atomistic systems","volume":"15","author":"Sch\u00fctt","year":"2018","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad4ae5bib16","article-title":"Schnet: a continuous-filter convolutional neural network for modeling quantum interactions","volume":"vol 30","author":"Sch\u00fctt","year":"2017"},{"article-title":"Equivariant message passing for the prediction of tensorial properties and molecular spectra","year":"2021","author":"Sch\u00fctt","key":"mlstad4ae5bib17"},{"key":"mlstad4ae5bib18","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1038\/s41467-023-36329-y","article-title":"Learning local equivariant representations for large-scale atomistic dynamics","volume":"14","author":"Musaelian","year":"2023","journal-title":"Nat. Commun."},{"key":"mlstad4ae5bib19","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2014.22","article-title":"Quantum chemistry structures and properties of 134 kilo molecules","volume":"1","author":"Ramakrishnan","year":"2014","journal-title":"Sci. Data"},{"key":"mlstad4ae5bib20","doi-asserted-by":"publisher","first-page":"5316","DOI":"10.1038\/s41467-019-13297-w","article-title":"Enhancing materials property prediction by leveraging computational and experimental data using deep transfer learning","volume":"10","author":"Jha","year":"2019","journal-title":"Nat. Commun."},{"key":"mlstad4ae5bib21","doi-asserted-by":"publisher","first-page":"1717","DOI":"10.1021\/acscentsci.9b00804","article-title":"Predicting materials properties with little data using shotgun transfer learning","volume":"5","author":"Yamada","year":"2019","journal-title":"ACS Cent. Sci."},{"key":"mlstad4ae5bib22","doi-asserted-by":"publisher","DOI":"10.1002\/adts.202000148","article-title":"Transfer learning as tool to enhance predictions of molecular properties based on 2d projections","volume":"3","author":"Lentelink","year":"2020","journal-title":"Adv. Theory Simul."},{"key":"mlstad4ae5bib23","doi-asserted-by":"publisher","first-page":"e1041","DOI":"10.7717\/peerj.1041","article-title":"Multi-level machine learning prediction of protein protein interactions in saccharomyces cerevisiae","volume":"3","author":"Zubek","year":"2015","journal-title":"PeerJ"},{"key":"mlstad4ae5bib24","doi-asserted-by":"publisher","first-page":"2087","DOI":"10.1021\/acs.jctc.5b00099","article-title":"Big data meets quantum chemistry approximations: the delta-machine learning approach","volume":"11","author":"Ramakrishnan","year":"2015","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad4ae5bib25","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1038\/s41570-020-0189-9","article-title":"Exploring chemical compound space with quantum-based machine learning","volume":"4","author":"von Lilienfeld","year":"2020","journal-title":"Nat. Rev. Chem."},{"key":"mlstad4ae5bib26","doi-asserted-by":"publisher","first-page":"4727","DOI":"10.1021\/acs.jcim.2c00760","article-title":"Cheap turns superior: a linear regression-based correction method to reaction energy from the DFT","volume":"62","author":"Nandi","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"mlstad4ae5bib27","doi-asserted-by":"publisher","DOI":"10.1063\/5.0158919","article-title":"Comparison of multifidelity machine learning models for potential energy surfaces","volume":"159","author":"Goodlett","year":"2023","journal-title":"J. Chem. Phys."},{"key":"mlstad4ae5bib28","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.1021\/acs.jctc.8b00832","article-title":"Boosting quantum machine learning models with a multilevel combination technique: pople diagrams revisited","volume":"15","author":"Zaspel","year":"2018","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad4ae5bib29","first-page":"pp 327","article-title":"Learning curves: asymptotic values and rate of convergence","author":"Cortes","year":"1994"},{"key":"mlstad4ae5bib30","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1126\/science.abn3445","article-title":"The central role of density functional theory in the AI age","volume":"381","author":"Huang","year":"2023","journal-title":"Science"},{"year":"1998","author":"Vapnik","key":"mlstad4ae5bib31"},{"first-page":"pp I\u2013XVIII, 1","year":"2006","author":"Rasmussen","key":"mlstad4ae5bib32"},{"article-title":"Qml: a python toolkit for quantum machine learning","year":"2017","author":"Christensen","key":"mlstad4ae5bib33"},{"year":"2020","author":"Deisenroth","key":"mlstad4ae5bib34"},{"year":"2020","author":"Sch\u00fctt","key":"mlstad4ae5bib35"},{"key":"mlstad4ae5bib36","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/15\/9\/095003","article-title":"Machine learning of molecular electronic properties in chemical compound space","volume":"15","author":"Montavon","year":"2013","journal-title":"New J. Phys."},{"key":"mlstad4ae5bib37","doi-asserted-by":"publisher","first-page":"8732","DOI":"10.1021\/ja902302h","article-title":"970 million druglike small molecules for virtual screening in the chemical universe database GDB-13","volume":"131","author":"Blum","year":"2009","journal-title":"J. Am. Chem. Soc."},{"key":"mlstad4ae5bib38","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"mlstad4ae5bib39","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1021\/ci00067a005","article-title":"SMILES. 3. DEPICT. Graphical depiction of chemical structures","volume":"30","author":"Weininger","year":"1990","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"mlstad4ae5bib40","doi-asserted-by":"publisher","DOI":"10.1021\/ja00051a040","article-title":"Uff, a full periodic table force field for molecular mechanics and molecular dynamics simulations","volume":"114","author":"Rappe","year":"1992","journal-title":"J. Am. Chem. Soc."},{"key":"mlstad4ae5bib41","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1186\/1758-2946-3-33","article-title":"Open babel: an open chemical toolbox","volume":"3","author":"O\u2019Boyle","year":"2011","journal-title":"J. Chem."},{"key":"mlstad4ae5bib42","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1103\/physrevlett.77.3865","article-title":"Generalized gradient approximation made simple","volume":"77","author":"Perdew","year":"1996","journal-title":"Phys. Rev. Lett."},{"article-title":"The fhi-aims code: all-electron, ab initio materials simulations towards the exascale","year":"2022","author":"Blum","key":"mlstad4ae5bib43"},{"key":"mlstad4ae5bib44","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","article-title":"Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17","volume":"52","author":"Ruddigkeit","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"mlstad4ae5bib45","doi-asserted-by":"publisher","first-page":"5648","DOI":"10.1063\/1.464913","article-title":"Density-functional thermochemistry. III. The role of exact exchange","volume":"98","author":"Becke","year":"1993","journal-title":"J. Chem. Phys."},{"key":"mlstad4ae5bib46","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1103\/PhysRevB.37.785","article-title":"Development of the colle-salvetti correlation-energy formula into a functional of the electron density","volume":"37","author":"Lee","year":"1988","journal-title":"Phys. Rev. B"},{"key":"mlstad4ae5bib47","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.commatsci.2015.02.050","article-title":"The electrolyte genome project: a big data approach in battery materials discovery","volume":"103","author":"Qu","year":"2015","journal-title":"Comput. Mater. Sci."},{"key":"mlstad4ae5bib48","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1017\/s0305004100011920","article-title":"The wave mechanics of an atom with a non-coulomb central field. Part II. Some results and discussion","volume":"24","author":"Hartree","year":"1928","journal-title":"Math. Proc. Camb. Phil. Soc."},{"key":"mlstad4ae5bib49","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1103\/physrev.32.339","article-title":"The self consistent field and the structure of atoms","volume":"32","author":"Slater","year":"1928","journal-title":"Phys. Rev."},{"key":"mlstad4ae5bib50","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1016\/0009-2614(90)80029-d","article-title":"A direct MP2 gradient method","volume":"166","author":"Frisch","year":"1990","journal-title":"Chem. Phys. Lett."},{"key":"mlstad4ae5bib51","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/0009-2614(88)85250-3","article-title":"MP2 energy evaluation by direct methods","volume":"153","author":"Head-Gordon","year":"1988","journal-title":"Chem. Phys. Lett."},{"key":"mlstad4ae5bib52","doi-asserted-by":"publisher","first-page":"2657","DOI":"10.1063\/1.1672392","article-title":"Self-consistent molecular-orbital methods. I. Use of gaussian expansions of slater-type atomic orbitals","volume":"51","author":"Hehre","year":"1969","journal-title":"J. Chem. Phys."},{"key":"mlstad4ae5bib53","doi-asserted-by":"publisher","first-page":"5142","DOI":"10.1063\/1.432189","article-title":"Self-consistent molecular orbital methods. XVII. Geometries and binding energies of second-row molecules. a comparison of three basis sets","volume":"64","author":"Collins","year":"1976","journal-title":"J. Chem. Phys."},{"key":"mlstad4ae5bib54","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1063\/1.1674902","article-title":"Self-consistent molecular-orbital methods. IX. An extended gaussian-type basis for molecular-orbital studies of organic molecules","volume":"54","author":"Ditchfield","year":"1971","journal-title":"J. Chem. Phys."},{"key":"mlstad4ae5bib55","doi-asserted-by":"publisher","first-page":"6796","DOI":"10.1063\/1.462569","article-title":"Electron affinities of the first-row atoms revisited. Systematic basis sets and wave functions","volume":"96","author":"Kendall","year":"1992","journal-title":"J. Chem. Phys."},{"year":"2009","author":"Frisch","key":"mlstad4ae5bib56"},{"key":"mlstad4ae5bib57","doi-asserted-by":"publisher","first-page":"e1606","DOI":"10.1002\/wcms.1606","article-title":"Software update: the orca program system version 5.0","volume":"12","author":"Neese","year":"2022","journal-title":"WIREs Comput. Mol. Sci."},{"key":"mlstad4ae5bib58","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2022-fs70n-v2)","article-title":"Large dataset of molecular and reaction energies from multi-level quantum chemical methods","author":"Nandi","year":"2022"},{"key":"mlstad4ae5bib59","doi-asserted-by":"publisher","DOI":"10.11583\/DTU.C.6185986)","article-title":"Multixc-qm9","author":"Nandi","year":"2022"},{"key":"mlstad4ae5bib60","first-page":"2825","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"mlstad4ae5bib61","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1162\/neco.1996.8.5.1085","article-title":"A numerical study on learning curves in stochastic multilayer feedforward networks","volume":"8","author":"M\u00fcller","year":"1996","journal-title":"Nuovo Cimento"},{"key":"mlstad4ae5bib62","doi-asserted-by":"publisher","first-page":"5255","DOI":"10.1021\/acs.jctc.7b00577","article-title":"Prediction errors of molecular machine learning models lower than hybrid dft error","volume":"13","author":"Faber","year":"2017","journal-title":"J. Chem. Theory Comput."},{"key":"mlstad4ae5bib63","first-page":"pp 195","article-title":"A comprehensive overview of the DFT-d3 london-dispersion correction","author":"Goerigk","year":"2017"},{"key":"mlstad4ae5bib64","doi-asserted-by":"publisher","DOI":"10.1039\/c7cp04913g","article-title":"A look at the density functional theory zoo with the advanced GMTKN55 database for general main group thermochemistry, kinetics and noncovalent interactions","volume":"19","author":"Goerigk","year":"2017","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstad4ae5bib65","doi-asserted-by":"publisher","DOI":"10.5281\/ZENODO.8252499","article-title":"Supplementary information for: reducing training data needs with minimal multilevel machine learning (m3l)","author":"Heinen","year":"2023"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4ae5","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4ae5\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4ae5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4ae5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4ae5\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4ae5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4ae5\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4ae5\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T09:07:55Z","timestamp":1717664875000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4ae5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,1]]},"references-count":65,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,6,6]]},"published-print":{"date-parts":[[2024,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad4ae5","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2024,6,1]]},"assertion":[{"value":"Reducing training data needs with minimal multilevel machine learning (M3L)","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":"2023-09-06","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-05-09","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-06-06","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}