{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T07:33:48Z","timestamp":1773992028730,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T00:00:00Z","timestamp":1736640000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T00:00:00Z","timestamp":1736640000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100002386","name":"Cairo University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100002386","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2025,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Optimizing neural network architectures through effective pruning techniques has become essential to balancing model complexity and accuracy. This study introduces a novel correlation-based approach to systematically reduce network size by identifying and removing redundant neurons based on their activation correlations. By selectively pruning neurons while compensating for their contributions, the method maintains model fidelity across diverse datasets. Results demonstrate substantial architecture reductions with minimal performance impact: For the MNIST dataset, the number of neurons in hidden layers was reduced from 128-128 to 118-93, while maintaining a high accuracy of 97.59%. Comparative analysis indicates that this pruning approach achieves competitive or superior results compared to state-of-the-art methods while reducing computational complexity and memory requirements by up to 25%. The findings highlight the potential of correlation-driven pruning strategies to optimize neural networks, making them more efficient and adaptable to resource-constrained environments.<\/jats:p>","DOI":"10.1007\/s00521-024-10932-6","type":"journal-article","created":{"date-parts":[[2025,1,12]],"date-time":"2025-01-12T15:51:24Z","timestamp":1736697084000},"page":"6351-6367","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Correlation-based pruning algorithm with weight compensation for feedforward neural networks"],"prefix":"10.1007","volume":"37","author":[{"given":"Shaimaa E. K.","family":"Ebid","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samah","family":"El-Tantawy","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Doaa","family":"Shawky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hany L.","family":"Abdel-Malek","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,12]]},"reference":[{"key":"10932_CR1","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1016\/j.eswa.2018.08.038","volume":"116","author":"J Yang","year":"2019","unstructured":"Yang J, Ma J (2019) Feed-forward neural network training using sparse representation. Expert Syst. Appl. 116:255\u2013264","journal-title":"Expert Syst. Appl."},{"key":"10932_CR2","doi-asserted-by":"crossref","unstructured":"J. Guo, K. Han, H. Wu, Y. Tang, X. Chen, Y. Wang, C. Xu, CMT: convolutional neural networks meet vision transformers, in Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"10932_CR3","doi-asserted-by":"publisher","first-page":"4149","DOI":"10.1007\/s11771-023-5514-2","volume":"30","author":"MN Aslam","year":"2023","unstructured":"Aslam MN, Riaz A, Shaukat N, Ali S, Akram S, Bhatti MM (2023) Analysis of incompressible viscous fluid flow in convergent and divergent channels with a hybrid meta-heuristic optimization techniques in ANN: an intelligent approach. J. Central South Univ. 30:4149\u20134167","journal-title":"J. Central South Univ."},{"key":"10932_CR4","doi-asserted-by":"publisher","first-page":"103740","DOI":"10.1016\/j.csite.2023.103740","volume":"52","author":"MN Aslam","year":"2023","unstructured":"Aslam MN, Shaheen A, Riaz A, Alshaikey S, Shaukat N, Aslam MW, Muhammed T (2023) An ANN-PSO approach for mixed convection flow in an inclined tube with ciliary motion of Jeffrey six constant fluid. Case Stud. Therm. Eng. 52:103740","journal-title":"Case Stud. Therm. Eng."},{"key":"10932_CR5","doi-asserted-by":"publisher","first-page":"49","DOI":"10.3390\/a17010049","volume":"17","author":"M Nayyeri","year":"2024","unstructured":"Nayyeri M, Rouhani M, Yazdi HS, M\u00e4kel\u00e4 MM, Maskooki A, Nikulin Y (2024) Correntropy-based constructive one hidden layer neural network. Algorithms 17:49","journal-title":"Algorithms"},{"key":"10932_CR6","doi-asserted-by":"publisher","first-page":"18143","DOI":"10.1007\/s00521-019-04196-8","volume":"32","author":"R Zemouri","year":"2020","unstructured":"Zemouri R, Omri N, Fnaiech F, Zerhouni N, Fnaiech N (2020) A new growing pruning deep learning neural network algorithm (GP-DLNN). Neural Comput. Appl. 32:18143\u201318159","journal-title":"Neural Comput. Appl."},{"key":"10932_CR7","doi-asserted-by":"publisher","first-page":"112875","DOI":"10.1016\/j.eswa.2019.112875","volume":"140","author":"K Akyol","year":"2020","unstructured":"Akyol K (2020) Comparing of deep neural networks and extreme learning machines based on growing and pruning approach. Expert Syst. Appl. 140:112875","journal-title":"Expert Syst. Appl."},{"key":"10932_CR8","first-page":"105","volume":"3","author":"MG Augasta","year":"2013","unstructured":"Augasta MG, Kathirvalavakumar T (2013) Pruning algorithms of neural networks\u2014a comparative study. Cenral Eur. J. Comput. Sci. 3:105\u2013115","journal-title":"Cenral Eur. J. Comput. Sci."},{"issue":"10\u201312","key":"10932_CR9","doi-asserted-by":"publisher","first-page":"2281","DOI":"10.1016\/j.neucom.2007.09.016","volume":"71","author":"AB Nielsen","year":"2008","unstructured":"Nielsen AB, Hansen LK (2008) Structure learning by pruning in independent component analysis. Neurocomputing 71(10\u201312):2281\u20132290","journal-title":"Neurocomputing"},{"key":"10932_CR10","doi-asserted-by":"publisher","first-page":"105580","DOI":"10.1016\/j.engappai.2022.105580","volume":"117","author":"K Zhou","year":"2023","unstructured":"Zhou K, Oh SK, Pedrycz W, Qiu J (2023) Data preprocessing strategy in constructing convolutional neural network classifier based on constrained particle swarm optimization with fuzzy penalty function. Eng. Appl. Artif. Intell. 117:105580","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10932_CR11","unstructured":"T.Q. Huynh, R. Setiono, Effective neural network pruning using cross validation, in IEEE International Joint Conference on Neural Networks, Montreal, QC, Canada (2005)"},{"key":"10932_CR12","doi-asserted-by":"publisher","first-page":"394","DOI":"10.1016\/j.knosys.2012.08.024","volume":"37","author":"Q Dai","year":"2013","unstructured":"Dai Q (2013) A competitive ensemble pruning approach based on cross-validation technique. Knowl. Based Syst. 37:394\u2013414","journal-title":"Knowl. Based Syst."},{"key":"10932_CR13","doi-asserted-by":"crossref","unstructured":"Sietsma, Dow, Neural net pruning: why and how,\" in IEEE International Conference on Neural Networks, Diego, CA, USA (1988)","DOI":"10.1109\/ICNN.1988.23864"},{"key":"10932_CR14","doi-asserted-by":"crossref","unstructured":"H. Yang, M. Tang, W. Wen, F. Yan, D. Hu, A. Li, H. Li, Y. Chen, Learning low-rank deep neural networks via singular vector orthogonality regularization and singular value sparsification, in IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2020)","DOI":"10.1109\/CVPRW50498.2020.00347"},{"key":"10932_CR15","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1016\/j.neucom.2020.03.082","volume":"404","author":"Z Wang","year":"2020","unstructured":"Wang Z, Li F, Shi G, Xie X, Wang F (2020) Network pruning using sparse learning and genetic algorithm. Neurocomputing 404:247\u2013256","journal-title":"Neurocomputing"},{"key":"10932_CR16","doi-asserted-by":"crossref","unstructured":"C. Yang, Z. An, C. Li, B. Diao, Y. Xu, Multi-objective pruning for CNNs using genetic algorithm, in Artificial Neural Networks and Machine Learning (ICANN): Deep Learning, Munich, Germany (2019)","DOI":"10.1007\/978-3-030-30484-3_25"},{"key":"10932_CR17","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1142\/S0218001409007132","volume":"23","author":"O Aran","year":"2009","unstructured":"Aran O, Yildiz OT, Alpaydin E (2009) An incremental framework based on cross validation for estimating the architecture of a multilayer perceprtron. Int. J. Pattern Recognit. Artif. Intell. 23:159\u2013190","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"10932_CR18","doi-asserted-by":"crossref","unstructured":"P. Molchanov, A. Mallya, S. Tyree, L. Frosio, J. Kautz, Importance estimation for neural network pruning, in IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01152"},{"issue":"2","key":"10932_CR19","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1016\/0925-2312(94)E0053-T","volume":"7","author":"LM Belue","year":"1995","unstructured":"Belue LM, Bauer KW Jr (1995) Determining input features for multilayer perceptrons. Neurocomputing 7(2):111\u2013121","journal-title":"Neurocomputing"},{"key":"10932_CR20","unstructured":"Z. Zhu, H. Chen, Z. Jin, X. Wang, J. Zhang, M. Xue, Q. Lu, J. Shen, K.-K. R. Choo, Adaptive knowledge transfer for neural network pruning, in CIKM\u201923: Proceedings of the 32nd ACM International Conference on Information and Knowledge Management, Canada (2023)"},{"key":"10932_CR21","doi-asserted-by":"publisher","first-page":"107707","DOI":"10.1016\/j.asoc.2021.107707","volume":"111","author":"K Xiang","year":"2021","unstructured":"Xiang K, Peng L, Yang H, Li M, Cao Z, Jiang S, Qu G (2021) A novel weight pruning strategy for light weight neural networks with application to the diagnosis of skin disease. Appl. Soft Comput. 111:107707","journal-title":"Appl. Soft Comput."},{"issue":"2","key":"10932_CR22","first-page":"622","volume":"205","author":"J-F Qiao","year":"2008","unstructured":"Qiao J-F, Zhang Y, Han H-G (2008) Fast unit pruning algorithm for feedforward neural network design. Appl. Math. Comput. 205(2):622\u2013627","journal-title":"Appl. Math. Comput."},{"key":"10932_CR23","doi-asserted-by":"crossref","unstructured":"C. Yang, Z. An, C. Li, B. Diao, Y. Xu, Multi-objective pruning for CNNs using genetic algorithm, in Lecture Notes in Computer Science (Springer, Cham, 2019), pp. 299\u2013305","DOI":"10.1007\/978-3-030-30484-3_25"},{"key":"10932_CR24","doi-asserted-by":"publisher","first-page":"8675","DOI":"10.1007\/s00521-019-04359-7","volume":"32","author":"KMR Alam","year":"2020","unstructured":"Alam KMR, Siddique N, Adeli H (2020) A dynamic ensemble learning algorithm for neural networks. Neural Comput. Appl. 32:8675\u20138690","journal-title":"Neural Comput. Appl."},{"key":"10932_CR25","doi-asserted-by":"publisher","first-page":"242","DOI":"10.1016\/j.inffus.2014.02.006","volume":"20","author":"SR Kheradpisheh","year":"2014","unstructured":"Kheradpisheh SR, Sharifizadeh F, Dalini AN, Ganjtabesh M, Ebrahimpour R (2014) Mixture of feature specified experts. Inf. Fusion 20:242\u2013251","journal-title":"Inf. Fusion"},{"key":"10932_CR26","unstructured":"L. Armi, E. Abbasi, J. Zarepour, Mixture of ELM based experts with trainable gating network, arXiv preprint (2021)"},{"issue":"9","key":"10932_CR27","doi-asserted-by":"publisher","first-page":"457","DOI":"10.14445\/22315381\/IJETT-V28P286","volume":"28","author":"S Pandey","year":"2015","unstructured":"Pandey S, Gour DK, Sharma V (2015) Comparative study on classification of thyroid diseases. Int. J. Eng. Trends Technol. (IJETT) 28(9):457\u2013460","journal-title":"Int. J. Eng. Trends Technol. (IJETT)"},{"key":"10932_CR28","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/BF00114162","volume":"6","author":"PW Frey","year":"1991","unstructured":"Frey PW, Slate DJ (1991) Letter recognition using Holland-style adaptive classifiers. Mach. Learn. 6:161\u2013182","journal-title":"Mach. Learn."},{"key":"10932_CR29","unstructured":"Y. Lecun, C. Cortes, C.J.C. Burges, The MNIST database of handwritten digits (2010). [Online]. Available: http:\/\/yann.lecun.com\/exdb\/mnist\/"},{"key":"10932_CR30","doi-asserted-by":"crossref","unstructured":"S. Pocos, I. Beckova, I. Farkas, Examining the proximity of adversarial examples to class manifolds in deep networks, in Artificial Neural Networks and Machine Learning-ICANN 2022 (Springer, 2022), pp. 645\u2013656","DOI":"10.1007\/978-3-031-15937-4_54"},{"key":"10932_CR31","doi-asserted-by":"crossref","unstructured":"S. Ismail, A.R. Zainal, A. Mustapha, Behavioural features for mushroom classification, in 2018 IEEE Symposium on Computer Applications & Industrial Electronics (ISCAIE), Penang, Malaysia (2018)","DOI":"10.1109\/ISCAIE.2018.8405508"},{"issue":"1","key":"10932_CR32","doi-asserted-by":"publisher","first-page":"47","DOI":"10.2298\/CSIS201221043N","volume":"19","author":"S Nayak","year":"2022","unstructured":"Nayak S, Panigrahi CR, Pati B, Nanda S, Hsieh MY (2022) Comparative analysis of HAR datasets using classification algorithms. Comput. Sci. Inf. Syst. 19(1):47\u201363","journal-title":"Comput. Sci. Inf. Syst."}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10932-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10932-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10932-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T13:58:04Z","timestamp":1741269484000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10932-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,12]]},"references-count":32,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["10932"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10932-6","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,12]]},"assertion":[{"value":"29 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 January 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 declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}