{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T11:10:02Z","timestamp":1757589002879,"version":"3.41.2"},"reference-count":60,"publisher":"Springer Science and Business Media LLC","issue":"20","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"CogniGron research center"},{"name":"Ubbo Emmius Funds"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Ensemble learning for artificial neural networks (ANNs) is an effective method to enhance predictive performance. However, ANNs are computationally and memory intensive, and naively training multiple networks can lead to excessive training times and costs. An effective tool for improving ensemble efficiency is introducing topological sparsity. Even though several implementations of efficient ensembles have been proposed, none of them can provide actual benefits in terms of computational overhead as the sparsity is simulated using binary masks. In this paper, we address this issue by introducing a Truly Sparse Ensemble without binary masks and directly incorporate native sparsity. We also propose two algorithms for initializing new subnetworks within the ensemble, leveraging this native topological sparsity to enhance subnetwork diversity. We demonstrate the performance of the resulting models at high levels of sparsity on several datasets in terms of classification accuracy, floating point operations (FLOPs), and actual running time. The proposed methods outperform all baseline dense and truly sparse models on tabular data, successfully diversify the training trajectory of the subnetworks, and increase the topological distance between subnetworks after re-initialization.<\/jats:p>","DOI":"10.1007\/s00521-025-11294-3","type":"journal-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T10:33:05Z","timestamp":1747996385000},"page":"15419-15438","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Multilayer perceptron ensembles in a truly sparse training context"],"prefix":"10.1007","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4958-1728","authenticated-orcid":false,"given":"Peter R. D.","family":"van der Wal","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7478-3509","authenticated-orcid":false,"given":"Nicola","family":"Strisciuglio","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6552-2596","authenticated-orcid":false,"given":"George","family":"Azzopardi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5636-7683","authenticated-orcid":false,"given":"Decebal Constatin","family":"Mocanu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"issue":"2","key":"11294_CR1","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s11704-019-8208-z","volume":"14","author":"X Dong","year":"2020","unstructured":"Dong X, Yu Z, Cao W, Shi Y, Ma Q (2020) A survey on ensemble learning. Front Comp Sci 14(2):241\u2013258. https:\/\/doi.org\/10.1007\/s11704-019-8208-z","journal-title":"Front Comp Sci"},{"key":"11294_CR2","unstructured":"Gale T, Elsen E, Hooker S (2019) The state of sparsity in deep neural networks. CoRR abs\/1902.09574. arXiv:1902.09574"},{"issue":"44","key":"11294_CR3","doi-asserted-by":"publisher","first-page":"19008","DOI":"10.1073\/pnas.1012590107","volume":"107","author":"S Herculano-Houzel","year":"2010","unstructured":"Herculano-Houzel S, Mota B, Wong P, Kaas JH (2010) Connectivity-driven white matter scaling and folding in primate cerebral cortex. Proc Natl Acad Sci 107(44):19008\u201319013","journal-title":"Proc Natl Acad Sci"},{"key":"11294_CR4","unstructured":"Frankle J, Carbin M (2018) The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks. https:\/\/openreview.net\/forum?id=rJl-b3RcF7"},{"key":"11294_CR5","unstructured":"Sokar G, Atashgahi Z, Pechenizkiy M, Mocanu DC (2022) Where to Pay Attention in Sparse Training for Feature Selection?. https:\/\/openreview.net\/forum?id=xWvI9z37Xd"},{"issue":"7","key":"11294_CR6","doi-asserted-by":"publisher","first-page":"2589","DOI":"10.1007\/s00521-020-05136-7","volume":"33","author":"S Liu","year":"2021","unstructured":"Liu S, Mocanu DC, Matavalam ARR, Pei Y, Pechenizkiy M (2021) Sparse evolutionary deep learning with over one million artificial neurons on commodity hardware. Neural Comput Appl 33(7):2589\u20132604. https:\/\/doi.org\/10.1007\/s00521-020-05136-7","journal-title":"Neural Comput Appl"},{"issue":"14","key":"11294_CR7","doi-asserted-by":"publisher","first-page":"15856","DOI":"10.1109\/JSEN.2023.3280485","volume":"23","author":"M Putra","year":"2023","unstructured":"Putra M, Hermawan A, Kim DS, Lee JM (2023) Data prediction-based energy-efficient architecture for industrial IoT. IEEE Sens J 23(14):15856\u201315866. https:\/\/doi.org\/10.1109\/JSEN.2023.3280485","journal-title":"IEEE Sens J"},{"key":"11294_CR8","doi-asserted-by":"publisher","DOI":"10.3390\/jlpea13030047","author":"J Dix","year":"2023","unstructured":"Dix J, Holleman J, Blalock B (2023) Programmable energy-efficient analog multilayer perceptron architecture suitable for future expansion to hardware accelerators. J Low Power Electron Appl. https:\/\/doi.org\/10.3390\/jlpea13030047","journal-title":"J Low Power Electron Appl"},{"issue":"2\u20133","key":"11294_CR9","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s10994-016-5570-z","volume":"104","author":"DC Mocanu","year":"2016","unstructured":"Mocanu DC, Mocanu E, Nguyen PH, Gibescu M, Liotta A (2016) A topological insight into restricted Boltzmann machines. Mach Learn 104(2\u20133):243\u2013270","journal-title":"Mach Learn"},{"key":"11294_CR10","unstructured":"Liu B, Wang M, Foroosh H, Tappen M, Pensky M (2015) Sparse convolutional neural networks, In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 806\u2013814"},{"key":"11294_CR11","doi-asserted-by":"publisher","unstructured":"Bibikar S, Vikalo H, Wang Z, Chen X (2022) Federated dynamic sparse training: Computing less, communicating less, yet learning better. Proceedings of the AAAI Conference on Artificial Intelligence 36(6):6080\u20136088. https:\/\/doi.org\/10.1609\/aaai.v36i6.20555","DOI":"10.1609\/aaai.v36i6.20555"},{"key":"11294_CR12","unstructured":"Liu J, Xu Z, Shi R, Cheung RCC, So HK (2020) Dynamic Sparse Training: Find Efficient Sparse Network From Scratch With Trainable Masked Layers, in International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SJlbGJrtDB"},{"key":"11294_CR13","doi-asserted-by":"publisher","unstructured":"Wu B, Yu T, Chen K, Liu W (2024) Edge-side fine-grained sparse cnn accelerator with efficient dynamic pruning scheme. IEEE Transactions on Circuits and Systems I: Regular Papers pp. 1\u201314. https:\/\/doi.org\/10.1109\/TCSI.2023.3347417","DOI":"10.1109\/TCSI.2023.3347417"},{"key":"11294_CR14","doi-asserted-by":"crossref","unstructured":"Whitaker T, Whitley D (2022) Prune and tune ensembles: low-cost ensemble learning with sparse independent subnetworks. In Proceedings of the AAAI Conference on Artificial Intelligence 36:8638\u20138646","DOI":"10.1609\/aaai.v36i8.20842"},{"key":"11294_CR15","doi-asserted-by":"publisher","unstructured":"Cho M, Joshi A, Hegde C (2021) ESPN: Extremely Sparse Pruned Networks, In 2021 IEEE Data Science and Learning Workshop (DSLW), pp. 1\u20138. https:\/\/doi.org\/10.1109\/DSLW51110.2021.9523404","DOI":"10.1109\/DSLW51110.2021.9523404"},{"issue":"2","key":"11294_CR16","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1109\/72.80236","volume":"1","author":"E Karnin","year":"1990","unstructured":"Karnin E (1990) A simple procedure for pruning back-propagation trained neural networks. IEEE Trans Neural Networks 1(2):239\u2013242. https:\/\/doi.org\/10.1109\/72.80236. (Conference Name: IEEE Transactions on Neural Networks)","journal-title":"IEEE Trans Neural Networks"},{"key":"11294_CR17","unstructured":"LeCun Y, Denker J, Solla S (1989) Optimal Brain Damage, in Advances in Neural Information Processing Systems, vol.\u00a02, ed. by D.\u00a0Touretzky (Morgan-Kaufmann, 1989). https:\/\/proceedings.neurips.cc\/paper\/1989\/file\/6c9882bbac1c7093bd25041881277658-Paper.pdf"},{"key":"11294_CR18","unstructured":"Zhu M, Gupta S (2017) To prune, or not to prune: exploring the efficacy of pruning for model compression"},{"issue":"2","key":"11294_CR19","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1109\/JETCAS.2019.2910864","volume":"9","author":"S Dey","year":"2019","unstructured":"Dey S, Huang KW, Beerel PA, Chugg KM (2019) Pre-defined sparse neural networks with hardware acceleration. IEEE J Emerg Select Topics Circuits Syst 9(2):332\u2013345","journal-title":"IEEE J Emerg Select Topics Circuits Syst"},{"issue":"1","key":"11294_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-018-04316-3","volume":"9","author":"DC Mocanu","year":"2018","unstructured":"Mocanu DC, Mocanu E, Stone P, Nguyen PH, Gibescu M, Liotta A (2018) Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nat Commun 9(1):1\u201312","journal-title":"Nat Commun"},{"issue":"10","key":"11294_CR21","doi-asserted-by":"publisher","first-page":"2635","DOI":"10.1007\/s11263-023-01824-8","volume":"131","author":"S Liu","year":"2023","unstructured":"Liu S, Tian Y, Chen T, Shen L (2023) Don\u2019t be so dense: sparse-to-sparse Gan training without sacrificing performance. Int J Comput Vision 131(10):2635\u20132648. https:\/\/doi.org\/10.1007\/s11263-023-01824-8","journal-title":"Int J Comput Vision"},{"key":"11294_CR22","unstructured":"Evci U, Gale T, Menick J, Castro PS, Elsen E (2020) Rigging the lottery: Making all tickets winners, in International Conference on Machine Learning (PMLR, 2020), pp. 2943\u20132952"},{"key":"11294_CR23","doi-asserted-by":"publisher","unstructured":"Liu S, Ni\u2019Mah I, Menkovski V, Mocanu DC, Pechenizkiy M (2021) Efficient and effective training of sparse recurrent neural networks. Neural Computing and Applications 33(15):9625\u20139636. https:\/\/doi.org\/10.1007\/s00521-021-05727-yhttps:\/\/rdcu.be\/cegM5","DOI":"10.1007\/s00521-021-05727-y"},{"key":"11294_CR24","unstructured":"Dettmers T, Zettlemoyer L (2019) Sparse networks from scratch: Faster training without losing performance. CoRR abs\/1907.04840. arXiv:1907.04840"},{"key":"11294_CR25","first-page":"20838","volume":"34","author":"G Yuan","year":"2021","unstructured":"Yuan G, Ma X, Niu W, Li Z, Kong Z, Liu N, Gong Y, Zhan Z, He C, Jin Q et al (2021) Mest: accurate and fast memory-economic sparse training framework on the edge. Adv Neural Inf Process Syst 34:20838\u201320850","journal-title":"Adv Neural Inf Process Syst"},{"key":"11294_CR26","unstructured":"Mostafa H, Wang X (2019) Parameter efficient training of deep convolutional neural networks by dynamic sparse reparameterization, In International Conference on Machine Learning (PMLR, 2019), pp. 4646\u20134655"},{"key":"11294_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105151","volume":"115","author":"MA Ganaie","year":"2022","unstructured":"Ganaie MA, Hu M, Malik AK, Tanveer M, Suganthan PN (2022) Ensemble deep learning: a review. Eng Appl Artif Intell 115:105151","journal-title":"Eng Appl Artif Intell"},{"key":"11294_CR28","doi-asserted-by":"publisher","DOI":"10.1201\/9781003587774","volume-title":"Ensemble methods: foundations and algorithms","author":"ZH Zhou","year":"2025","unstructured":"Zhou ZH (2025) Ensemble methods: foundations and algorithms. CRC press"},{"issue":"1","key":"11294_CR29","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1109\/MCI.2015.2471235","volume":"11","author":"Y Ren","year":"2016","unstructured":"Ren Y, Zhang L, Suganthan P (2016) Ensemble classification and regression-recent developments, applications and future directions. IEEE Comput Intell Mag 11(1):41\u201353. https:\/\/doi.org\/10.1109\/MCI.2015.2471235. (Conference Name: IEEE Computational Intelligence Magazine)","journal-title":"IEEE Comput Intell Mag"},{"key":"11294_CR30","doi-asserted-by":"publisher","unstructured":"Sagi O, Rokach L (2018) Ensemble learning: A survey. WIREs Data Mining and Knowledge Discovery 8(4):e1249. https:\/\/doi.org\/10.1002\/widm.1249https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/widm.1249","DOI":"10.1002\/widm.1249"},{"key":"11294_CR31","doi-asserted-by":"publisher","unstructured":"Chandra A, Yao X (2004)DIVACE: Diverse and Accurate Ensemble Learning Algorithm, in Intelligent Data Engineering and Automated Learning \u2013 IDEAL 2004, ed. by Z.R. Yang, H.\u00a0Yin, R.M. Everson (Springer, Berlin, Heidelberg), Lecture Notes in Computer Science, pp. 619\u2013625. https:\/\/doi.org\/10.1007\/978-3-540-28651-6_91","DOI":"10.1007\/978-3-540-28651-6_91"},{"key":"11294_CR32","doi-asserted-by":"publisher","unstructured":"Chen S, Zhao R, Fu H (2021) Ensemble diversity enhancement based on parameters evolution of base learners, in 2021 33rd Chinese Control and Decision Conference (CCDC), pp. 5887\u20135893. https:\/\/doi.org\/10.1109\/CCDC52312.2021.9601781. ISSN: 1948-9447","DOI":"10.1109\/CCDC52312.2021.9601781"},{"key":"11294_CR33","doi-asserted-by":"publisher","unstructured":"Liu Y, Yao X (1999) Ensemble learning via negative correlation. Neural Networks 12(10):1399\u20131404. https:\/\/doi.org\/10.1016\/S0893-6080(99)00073-8https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0893608099000738","DOI":"10.1016\/S0893-6080(99)00073-8"},{"key":"11294_CR34","doi-asserted-by":"publisher","first-page":"10:1","DOI":"10.1145\/2379776.2379786","volume":"45","author":"J Moreira","year":"2012","unstructured":"Moreira J, Soares C, Jorge A, Sousa J (2012) Ensemble approaches for regression: a survey. ACM Comput Surv 45:10:1-10:40. https:\/\/doi.org\/10.1145\/2379776.2379786","journal-title":"ACM Comput Surv"},{"issue":"2","key":"11294_CR35","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00058655","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman L (1996) Bagging predictors. Mach Learn 24(2):123\u2013140. https:\/\/doi.org\/10.1007\/BF00058655","journal-title":"Mach Learn"},{"key":"11294_CR36","doi-asserted-by":"publisher","unstructured":"Webb G, Zheng Z (2004) Multistrategy Ensemble Learning: Reducing Error by Combining Ensemble Learning Techniques. Knowledge and Data Engineering, IEEE Transactions on 16:980\u2013991. https:\/\/doi.org\/10.1109\/TKDE.2004.29","DOI":"10.1109\/TKDE.2004.29"},{"issue":"8","key":"11294_CR37","doi-asserted-by":"publisher","first-page":"832","DOI":"10.1109\/34.709601","volume":"20","author":"TK Ho","year":"1998","unstructured":"Ho TK (1998) The random subspace method for constructing decision forests. IEEE Trans Pattern Anal Mach Intell 20(8):832\u2013844. https:\/\/doi.org\/10.1109\/34.709601. (Conference Name: IEEE Transactions on Pattern Analysis and Machine Intelligence)","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11294_CR38","doi-asserted-by":"crossref","unstructured":"Ho TK (1995) Random decision forests. In Proceedings of 3rd international conference on document analysis and recognition 1:278\u2013282 (IEEE)","DOI":"10.1109\/ICDAR.1995.598994"},{"key":"11294_CR39","unstructured":"Freund Y, Schapire R (1996) Experiments with a New Boosting Algorithm. undefined. https:\/\/api.semanticscholar.org\/CorpusID:1836349"},{"key":"11294_CR40","doi-asserted-by":"publisher","unstructured":"Freund Y, Schapire RE (1997) A Decision-Theoretic Generalization of On-Line Learning and an Application to Boosting. Journal of Computer and System Sciences 55(1):119\u2013139. https:\/\/doi.org\/10.1006\/jcss.1997.1504https:\/\/www.sciencedirect.com\/science\/article\/pii\/S002200009791504X","DOI":"10.1006\/jcss.1997.1504"},{"key":"11294_CR41","doi-asserted-by":"publisher","unstructured":"Wolpert DH (1992) Stacked generalization. Neural Networks 5(2):241\u2013259. https:\/\/doi.org\/10.1016\/S0893-6080(05)80023-1https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0893608005800231","DOI":"10.1016\/S0893-6080(05)80023-1"},{"key":"11294_CR42","doi-asserted-by":"crossref","unstructured":"Ciregan D, Meier U, Schmidhuber J (2012) Multi-column deep neural networks for image classification, in 2012 IEEE conference on computer vision and pattern recognition (IEEE), pp. 3642\u20133649","DOI":"10.1109\/CVPR.2012.6248110"},{"key":"11294_CR43","doi-asserted-by":"publisher","unstructured":"Harangi B, Baran A, Beregi-Kovacs M, Hajdu A (2023) Composing diverse ensembles of convolutional neural networks by penalization. Mathematics 11(23). https:\/\/doi.org\/10.3390\/math11234730https:\/\/www.mdpi.com\/2227-7390\/11\/23\/4730","DOI":"10.3390\/math11234730"},{"key":"11294_CR44","unstructured":"Lee S, Purushwalkam S, Cogswell M, Crandall D, Batra D (2015) Why m heads are better than one: Training a diverse ensemble of deep networks. arXiv preprint arXiv:1511.06314"},{"key":"11294_CR45","unstructured":"Abe T, Buchanan EK, Pleiss G, Cunningham JP (2023) Pathologies of predictive diversity in deep ensembles. arXiv preprint arXiv:2302.00704"},{"key":"11294_CR46","doi-asserted-by":"publisher","unstructured":"Kobayashi S, Kiyono S, Suzuki J, Inui K (2022) Diverse Lottery Tickets Boost Ensemble from a Single Pretrained Model, in Proceedings of BigScience Episode #5 \u2013 Workshop on Challenges & Perspectives in Creating Large Language Models (Association for Computational Linguistics, virtual+Dublin, 2022), pp. 42\u201350. https:\/\/doi.org\/10.18653\/v1\/2022.bigscience-1.4. https:\/\/aclanthology.org\/2022.bigscience-1.4","DOI":"10.18653\/v1\/2022.bigscience-1.4"},{"key":"11294_CR47","unstructured":"Liu S, Chen T, Atashgahi Z, Chen X, Sokar G, Mocanu E, Pechenizkiy M, Wang Z, Mocanu DC (2022) Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity, in ICLR"},{"key":"11294_CR48","doi-asserted-by":"publisher","unstructured":"Evci U, Ioannou Y, Keskin C, Dauphin Y (2022) Gradient Flow in Sparse Neural Networks and How Lottery Tickets Win. Proceedings of the AAAI Conference on Artificial Intelligence 36(6):6577\u20136586. https:\/\/doi.org\/10.1609\/aaai.v36i6.20611https:\/\/ojs.aaai.org\/index.php\/AAAI\/article\/view\/20611. Number: 6","DOI":"10.1609\/aaai.v36i6.20611"},{"key":"11294_CR49","unstructured":"Nikdan M, Pegolotti T, Iofinova E, Kurtic E, Alistarh D (2023) SparseProp: Efficient Sparse Backpropagation for Faster Training of Neural Networks at the Edge, in Proceedings of the 40th International Conference on Machine Learning, Proceedings of Machine Learning Research, vol. 202, ed. by A.\u00a0Krause, E.\u00a0Brunskill, K.\u00a0Cho, B.\u00a0Engelhardt, S.\u00a0Sabato, J.\u00a0Scarlett (PMLR, 2023), pp. 26215\u201326227. https:\/\/proceedings.mlr.press\/v202\/nikdan23a.html"},{"key":"11294_CR50","doi-asserted-by":"crossref","unstructured":"Atashgahi Z, Sokar G, van\u00a0der Lee T, Mocanu E, Mocanu DC, Veldhuis R, Pechenizkiy M (2022) Quick and robust feature selection: the strength of energy-efficient sparse training for autoencoders. Machine Learning pp. 1\u201338","DOI":"10.1007\/s10994-021-06063-x"},{"key":"11294_CR51","doi-asserted-by":"crossref","unstructured":"Curci S, Mocanu DC, Pechenizkiyi M (2021) Truly sparse neural networks at scale. arXiv preprint arXiv:2102.01732","DOI":"10.21203\/rs.3.rs-133395\/v1"},{"key":"11294_CR52","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","author":"P Virtanen","year":"2020","unstructured":"...Virtanen P, Gommers R, Oliphant TE, Haberland M, Reddy T, Cournapeau D, Burovski E, Peterson P, Weckesser W, Bright J, van der Walt SJ, Brett M, Wilson J, Millman KJ, Mayorov N, Nelson ARJ, Jones E, Kern R, Larson E, Carey CJ, Polat \u0130, Feng Y, Moore EW, VanderPlas J, Laxalde D, Perktold J, Cimrman R, Henriksen I, Quintero EA, Harris CR, Archibald AM, Ribeiro AH, Pedregosa F, van Mulbregt P (2020) SciPy 1.0 contributors, sciPy 1.0: fundamental algorithms for scientific computing in python. Nat Methods 17:261\u2013272. https:\/\/doi.org\/10.1038\/s41592-019-0686-2","journal-title":"Nat Methods"},{"key":"11294_CR53","doi-asserted-by":"publisher","unstructured":"Dietterich TG (2000) Ensemble Methods in Machine Learning, in Multiple Classifier Systems (Springer, Berlin, Heidelberg), Lecture Notes in Computer Science, pp. 1\u201315. https:\/\/doi.org\/10.1007\/3-540-45014-9_1","DOI":"10.1007\/3-540-45014-9_1"},{"key":"11294_CR54","unstructured":"Dua D, Graff C (2017) UCI machine learning repository. http:\/\/archive.ics.uci.edu\/ml"},{"key":"11294_CR55","doi-asserted-by":"crossref","unstructured":"Baldi P, Sadowski P, Whiteson D (2014) Searching for exotic particles in high-energy physics with deep learning. Nature Communications 5:4308 https:\/\/archive.ics.uci.edu\/ml\/datasets\/HIGGS","DOI":"10.1038\/ncomms5308"},{"key":"11294_CR56","unstructured":"Grinsztajn L, Oyallon E, Varoquaux G (2022) Why do tree-based models still outperform deep learning on typical tabular data?. https:\/\/openreview.net\/forum?id=Fp7__phQszn"},{"key":"11294_CR57","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1007\/978-3-642-11261-4_11","volume-title":"Tools for high performance computing 2009","author":"D Terpstra","year":"2010","unstructured":"Terpstra D, Jagode H, You H, Dongarra J (2010) Collecting Performance Data with PAPI-C. In: M\u00fcller MS, Resch MM, Schulz A, Nagel WE (eds) Tools for high performance computing 2009. Springer, Heidelberg, pp 157\u2013173"},{"key":"11294_CR58","unstructured":"Paszke A, Gross S, Chintala S, Chanan G, Yang E, DeVito Z, Lin Z, Desmaison A, Antiga L, Lerer A (2017) Automatic differentiation in pytorch"},{"key":"11294_CR59","unstructured":"Maaten Lvd, Hinton G (2008) Visualizing Data using t-SNE. Journal of Machine Learning Research 9(86), 2579\u20132605. http:\/\/jmlr.org\/papers\/v9\/vandermaaten08a.html"},{"key":"11294_CR60","doi-asserted-by":"crossref","unstructured":"Liu S, der Lee TV, Yaman A, Atashgahi Z, Ferraro D, Sokar G, Pechenizkiy M, Mocanu DC (2020) Topological insights into sparse neural networks, in Joint European conference on machine learning and knowledge discovery in databases (Springer), pp. 279\u2013294","DOI":"10.1007\/978-3-030-67664-3_17"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11294-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-025-11294-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-025-11294-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,7]],"date-time":"2025-07-07T11:06:59Z","timestamp":1751886419000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-025-11294-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":60,"journal-issue":{"issue":"20","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["11294"],"URL":"https:\/\/doi.org\/10.1007\/s00521-025-11294-3","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2025,5,23]]},"assertion":[{"value":"25 October 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 April 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2025","order":3,"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 conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}