{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T11:07:34Z","timestamp":1791544054144,"version":"4.3.4"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T00:00:00Z","timestamp":1719273600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T00:00:00Z","timestamp":1719273600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003825","name":"Magyar Tudom\u00e1nyos Akad\u00e9mia","doi-asserted-by":"publisher","award":["BO\/00233\/21\/6"],"award-info":[{"award-number":["BO\/00233\/21\/6"]}],"id":[{"id":"10.13039\/501100003825","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009567","name":"Budapest University of Technology and Economics","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100009567","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Artif Intell Rev"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Artificial Intelligence represents a rapidly expanding domain, with several industrial applications demonstrating its superiority over traditional techniques. Despite numerous advancements within the subfield of Machine Learning, it encounters persistent challenges, highlighting the importance of ongoing research efforts. Among its primary branches, this study delves into two categories, being Supervised and Reinforcement Learning, particularly addressing the common issue of data selection for training. The inherent variability in informational content among data points is apparent, wherein certain samples offer more valuable information to the neural network than others. However, evaluating the significance of various data points remains a non-trivial task, generating the need for a robust method to effectively prioritize samples. Drawing inspiration from Reinforcement Learning principles, this paper introduces a novel sample prioritization approach, applied to Supervised Learning scenarios, aimed at enhancing classification accuracy through strategic data navigation, while exploring the boundary between Reinforcement and Supervised Learning techniques. We provide a comprehensive description of our methodology while revealing the identification of an optimal prioritization balance and demonstrating its beneficial impact on model performance. Although classification accuracy serves as the primary validation metric, the concept of information density-based prioritization encompasses wider applicability. Additionally, the paper investigates parallels and distinctions between Reinforcement and Supervised Learning methods, declaring that the foundational principle is equally relevant, hence completely adaptable to Supervised Learning with appropriate adjustments due to different learning frameworks. The project page and source code are available at:\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" ext-link-type=\"uri\" xlink:href=\"https:\/\/csanadlb.github.io\/sl_prioritized_sampling\/\">https:\/\/csanadlb.github.io\/sl_prioritized_sampling\/<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1007\/s10462-024-10813-3","type":"journal-article","created":{"date-parts":[[2024,6,25]],"date-time":"2024-06-25T04:02:44Z","timestamp":1719288164000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Strategic data navigation: information value-based sample selection"],"prefix":"10.1007","volume":"57","author":[{"given":"Csan\u00e1d L.","family":"Balogh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B\u00e1lint","family":"Pelenczei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"B\u00e1lint","family":"K\u0151v\u00e1ri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tam\u00e1s","family":"B\u00e9csi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,6,25]]},"reference":[{"key":"10813_CR1","doi-asserted-by":"crossref","unstructured":"Beluch WH, Genewein T, N\u00fcrnberger A, et\u00a0al (2018) The power of ensembles for active learning in image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00976"},{"key":"10813_CR2","unstructured":"Brittain M, Bertram J, Yang X, et\u00a0al (2020) Prioritized sequence experience replay. arXiv: 1905.12726"},{"key":"10813_CR3","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1007\/s10489-013-0458-0","volume":"40","author":"E Cuevas","year":"2014","unstructured":"Cuevas E, Echavarr\u00eda A, Ram\u00edrez-Orteg\u00f3n MA (2014) An optimization algorithm inspired by the states of matter that improves the balance between exploration and exploitation. Appl Intell 40:256\u2013272. https:\/\/doi.org\/10.1007\/s10489-013-0458-0","journal-title":"Appl Intell"},{"issue":"9","key":"10813_CR4","doi-asserted-by":"publisher","first-page":"6390","DOI":"10.1109\/TNNLS.2021.3136503","volume":"34","author":"D Dablain","year":"2023","unstructured":"Dablain D, Krawczyk B, Chawla NV (2023) Deepsmote: fusing deep learning and smote for imbalanced data. IEEE Trans Neural Netw Learn Syst 34(9):6390\u20136404. https:\/\/doi.org\/10.1109\/TNNLS.2021.3136503","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10813_CR5","unstructured":"Foret P, Kleiner A, Mobahi H, et\u00a0al (2020) Sharpness-aware minimization for efficiently improving generalization. arXiv preprint arXiv:2010.01412"},{"key":"10813_CR6","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504","author":"Y Freund","year":"2002","unstructured":"Freund Y, Schapire R (2002) A decision-theoretic generalization of on-line learning and an application to boosting. J Comput Syst Sci. https:\/\/doi.org\/10.1006\/jcss.1997.1504","journal-title":"J Comput Syst Sci"},{"key":"10813_CR7","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s10994-008-5064-8","volume":"73","author":"J F\u00fcrnkranz","year":"2008","unstructured":"F\u00fcrnkranz J, H\u00fcllermeier E, Loza Menc\u00eda E et al (2008) Multilabel classification via calibrated label ranking. Mach Learn 73:133\u2013153. https:\/\/doi.org\/10.1007\/s10994-008-5064-8","journal-title":"Mach Learn"},{"issue":"3","key":"10813_CR8","doi-asserted-by":"publisher","first-page":"349","DOI":"10.4310\/SII.2009.v2.n3.a8","volume":"2","author":"T Hastie","year":"2009","unstructured":"Hastie T, Rosset S, Zhu J et al (2009) Multi-class adaboost. Stat Interface 2(3):349\u2013360","journal-title":"Stat Interface"},{"issue":"11","key":"10813_CR9","doi-asserted-by":"publisher","first-page":"6440","DOI":"10.1109\/TGRS.2018.2838665","volume":"56","author":"JM Haut","year":"2018","unstructured":"Haut JM, Paoletti ME, Plaza J et al (2018) Active learning with convolutional neural networks for hyperspectral image classification using a new Bayesian approach. IEEE Trans Geosci Remote Sens 56(11):6440\u20136461. https:\/\/doi.org\/10.1109\/TGRS.2018.2838665","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"10813_CR10","doi-asserted-by":"crossref","unstructured":"He K, Chen X, Xie S, et\u00a0al (2021) Masked autoencoders are scalable vision learners. arXiv: 2111.06377","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"10813_CR11","unstructured":"Horgan D, Quan J, Budden D, et\u00a0al (2018) Distributed prioritized experience replay. arXiv: 1803.00933"},{"key":"10813_CR12","unstructured":"Houlsby N, Husz\u00e1r F, Ghahramani Z, et\u00a0al (2011) Bayesian active learning for classification and preference learning. arXiv: 1112.5745"},{"key":"10813_CR13","unstructured":"Kirsch A, van Amersfoort J, Gal Y (2019) Batchbald: Efficient and diverse batch acquisition for deep bayesian active learning. In: Wallach H, Larochelle H, Beygelzimer A, et\u00a0al (eds) Advances in Neural Information Processing Systems, vol\u00a032. Curran Associates, Inc., https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/95323660ed2124450caaac2c46b5ed90-Paper.pdf"},{"key":"10813_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106694","author":"S Koh","year":"2020","unstructured":"Koh S, Zhou B, Fang H et al (2020) Real-time deep reinforcement learning based vehicle routing and navigation. Appl Soft Comput. https:\/\/doi.org\/10.1016\/j.asoc.2020.106694","journal-title":"Appl Soft Comput"},{"key":"10813_CR15","doi-asserted-by":"publisher","DOI":"10.3390\/app10207171","author":"B K\u0151v\u00e1ri","year":"2020","unstructured":"K\u0151v\u00e1ri B, Heged\u00fcs F, B\u00e9csi T (2020) Design of a reinforcement learning-based lane keeping planning agent for automated vehicles. Appl Sci. https:\/\/doi.org\/10.3390\/app10207171","journal-title":"Appl Sci"},{"key":"10813_CR16","doi-asserted-by":"publisher","first-page":"138488","DOI":"10.1109\/ACCESS.2023.3339248","volume":"11","author":"B K\u0151v\u00e1ri","year":"2023","unstructured":"K\u0151v\u00e1ri B, Pelenczei B, B\u00e9csi T (2023) Enhanced experience prioritization: a novel upper confidence bound approach. IEEE Access 11:138488\u2013138501. https:\/\/doi.org\/10.1109\/ACCESS.2023.3339248","journal-title":"IEEE Access"},{"key":"10813_CR17","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin Y, Cao Y, et\u00a0al (2021) Swin transformer: Hierarchical vision transformer using shifted windows. arXiv: 2103.14030","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10813_CR18","doi-asserted-by":"crossref","unstructured":"Liu Z, Li S, Wu D, et\u00a0al (2022a) Automix: Unveiling the power of mixup for stronger classifiers. arXiv: 2103.13027","DOI":"10.1007\/978-3-031-20053-3_26"},{"key":"10813_CR19","doi-asserted-by":"crossref","unstructured":"Liu Z, Mao H, Wu CY, et\u00a0al (2022b) A convnet for the 2020s. arXiv: 2201.03545","DOI":"10.1109\/CVPR52688.2022.01167"},{"issue":"10","key":"10813_CR20","doi-asserted-by":"publisher","first-page":"2134","DOI":"10.1109\/TNNLS.2016.2585520","volume":"27","author":"B Luo","year":"2016","unstructured":"Luo B, Liu D, Huang T et al (2016) Model-free optimal tracking control via critic-only q-learning. IEEE Trans Neural Netw Learn Syst 27(10):2134\u20132144. https:\/\/doi.org\/10.1109\/TNNLS.2016.2585520","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10813_CR21","unstructured":"Nguyen Q, Valizadegan H, Seybert A, et\u00a0al (2011) Sample-efficient learning with auxiliary class-label information. AMIA Annu Symp Proc"},{"key":"10813_CR22","doi-asserted-by":"crossref","unstructured":"Schapire RE (2013) Explaining adaboost. In: Empirical Inference: Festschrift in Honor of Vladimir N. Vapnik. Springer, Charm. 37\u201352","DOI":"10.1007\/978-3-642-41136-6_5"},{"key":"10813_CR23","unstructured":"Schaul T, Quan J, Antonoglou I, et\u00a0al (2016) Prioritized experience replay. arXiv: 1511.05952"},{"key":"10813_CR24","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/BF00115009","volume":"3","author":"R Sutton","year":"1988","unstructured":"Sutton R (1988) Learning to predict by the method of temporal differences. Mach Learn 3:9\u201344. https:\/\/doi.org\/10.1007\/BF00115009","journal-title":"Mach Learn"},{"key":"10813_CR25","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/7068349","author":"A Voulodimos","year":"2018","unstructured":"Voulodimos A, Doulamis N, Doulamis A et al (2018) Deep learning for computer vision: a brief review. Comput intell Neurosci. https:\/\/doi.org\/10.1155\/2018\/7068349","journal-title":"Comput intell Neurosci"},{"key":"10813_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TBCAS.2015.2500101","volume":"9","author":"Z Wang","year":"2015","unstructured":"Wang Z, Zhang J, Verma N (2015) Realizing low-energy classification systems by implementing matrix multiplication directly within an ADC. IEEE Trans Biomed Circuits Syst 9:1\u20131. https:\/\/doi.org\/10.1109\/TBCAS.2015.2500101","journal-title":"IEEE Trans Biomed Circuits Syst"},{"key":"10813_CR27","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-019-01073-3","author":"C Yan","year":"2020","unstructured":"Yan C, Xiaojia X, Wang C (2020) Towards real-time path planning through deep reinforcement learning for a UAV in dynamic environments. J Intell Robot Syst. https:\/\/doi.org\/10.1007\/s10846-019-01073-3","journal-title":"J Intell Robot Syst"},{"key":"10813_CR28","doi-asserted-by":"crossref","unstructured":"Yoo D, Kweon IS (2019) Learning loss for active learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2019.00018"},{"key":"10813_CR29","doi-asserted-by":"crossref","unstructured":"Yun S, Han D, Oh SJ, et\u00a0al (2019) Cutmix: regularization strategy to train strong classifiers with localizable features. arXiv: 1905.04899","DOI":"10.1109\/ICCV.2019.00612"}],"container-title":["Artificial Intelligence Review"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-024-10813-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10462-024-10813-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10462-024-10813-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T06:33:00Z","timestamp":1721025180000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10462-024-10813-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,25]]},"references-count":29,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2024,7]]}},"alternative-id":["10813"],"URL":"https:\/\/doi.org\/10.1007\/s10462-024-10813-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-4144238\/v1","asserted-by":"object"}]},"ISSN":["1573-7462"],"issn-type":[{"value":"1573-7462","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,6,25]]},"assertion":[{"value":"28 May 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no competing interests to declare relevant to this article\u2019s content.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Not applicable.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent to participate"}},{"value":"Not applicable.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}}],"article-number":"187"}}