{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T06:39:26Z","timestamp":1776753566159,"version":"3.51.2"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T00:00:00Z","timestamp":1776729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Evol. Intel."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s12065-026-01191-6","type":"journal-article","created":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:43:10Z","timestamp":1776750190000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Head optimizer: Heun\u2019s enhanced adaptive descent"],"prefix":"10.1007","volume":"19","author":[{"given":"Furqan Yaqub","family":"Khan","sequence":"first","affiliation":[]},{"given":"Tawseef Ayoub","family":"Shaikh","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,4,21]]},"reference":[{"key":"1191_CR1","unstructured":"Abdullah AA, Badawi S, Abdullah DA, Hamad DR (2025) From dialect gaps to identity maps: tackling variability in speaker verification. arXiv:2505.04629"},{"key":"1191_CR2","unstructured":"Abdullah DA, Hamad DR, Ibrahim BR, Aula SA, Ameen AK, Hamadamin SS (2025) Innovative deep learning architecture for enhanced altered fingerprint recognition. arXiv:2509.20537"},{"issue":"5","key":"1191_CR3","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2025.103350","volume":"16","author":"DA Abdullah","year":"2025","unstructured":"Abdullah DA, Hamad DR, Maolood IY, Beitollahi H, Ameen AK, Aula SA, Abdulla AA, Shakor MY, Muhamad SS (2025) A novel facial recognition technique with focusing on masked faces. Ain Shams Eng J 16(5):103350. https:\/\/doi.org\/10.1016\/j.asej.2025.103350. (ISSN 2090-4479)","journal-title":"Ain Shams Eng J"},{"key":"1191_CR4","unstructured":"Aula S, Rashid T (2025) A hybrid nature-inspired algorithm for Tourism Industry Data. PhD thesis, p 11"},{"key":"1191_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.sasc.2024.200178","volume":"6","author":"SA Aula","year":"2024","unstructured":"Aula SA, Rashid TA (2024) FOX-TSA hybrid algorithm: advancing for superior predictive accuracy in tourism-driven multi-layer perceptron models. Syst Soft Comput 6:200178. https:\/\/doi.org\/10.1016\/j.sasc.2024.200178. (ISSN 2772-9419)","journal-title":"Syst Soft Comput"},{"issue":"1","key":"1191_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.asej.2024.103185","volume":"16","author":"SA Aula","year":"2025","unstructured":"Aula SA, Rashid TA (2025) FOX-TSA: navigating complex search spaces and superior performance in benchmark and real-world optimization problems. Ain Shams Eng J 16(1):103185. https:\/\/doi.org\/10.1016\/j.asej.2024.103185. (ISSN 2090-4479)","journal-title":"Ain Shams Eng J"},{"key":"1191_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cogsys.2025.101373","volume":"92","author":"SA Aula","year":"2025","unstructured":"Aula SA, Rashid TA (2025) Foxtsage vs. Adam: revolution or evolution in optimization? Cogn Syst Res 92:101373. https:\/\/doi.org\/10.1016\/j.cogsys.2025.101373","journal-title":"Cogn Syst Res"},{"key":"1191_CR8","doi-asserted-by":"crossref","unstructured":"Bahram AM, Omer SM, Mohammed HM, Aula SA (2025) Enhanced chest disease classification using an improved CheXNet framework with EfficientNetV2-M and optimization-driven learning. arXiv:2512.08992","DOI":"10.2139\/ssrn.5867896"},{"key":"1191_CR9","doi-asserted-by":"crossref","unstructured":"Bottou L (2010) Large-scale machine learning with stochastic gradient descent. In: Proceedings of COMPSTAT. Springer, pp 177\u2013186","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"1191_CR10","doi-asserted-by":"publisher","DOI":"10.1002\/9780470753767","volume-title":"Numerical methods for ordinary differential equations","author":"JC Butcher","year":"2008","unstructured":"Butcher JC (2008) Numerical methods for ordinary differential equations. Wiley, New York"},{"key":"1191_CR11","first-page":"2121","volume":"12","author":"JC Duchi","year":"2011","unstructured":"Duchi JC, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121\u20132159","journal-title":"J Mach Learn Res"},{"key":"1191_CR12","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"1191_CR13","first-page":"1","volume":"45","author":"K Heun","year":"1900","unstructured":"Heun K (1900) Neue methode zur approximate-integration von differentialgleichungen einer unabhangigen veranderlichen. Z Math Phys 45:1\u20134","journal-title":"Z Math Phys"},{"key":"1191_CR14","unstructured":"Hinton G (2012) Lecture $$6e$$ rmsprop: divide the gradient by a running average of its recent magnitude, 2012. Lecture notes, neural networks for machine learning"},{"key":"1191_CR15","doi-asserted-by":"publisher","first-page":"1639720","DOI":"10.3389\/frai.2025.1639720","volume":"8","author":"MA Jumaah","year":"2025","unstructured":"Jumaah MA, Ali YH, Rashid TA (2025) Artificial liver classifier: a new alternative to conventional machine learning models. Front Artif Intell 8:1639720. https:\/\/doi.org\/10.3389\/frai.2025.1639720","journal-title":"Front Artif Intell"},{"key":"1191_CR16","unstructured":"Kingma DP, Adam JB (2015) A method for stochastic optimization. In: International conference on learning representations (ICLR). arXiv:1412.6980"},{"key":"1191_CR17","unstructured":"Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. https:\/\/www.cs.toronto.edu\/~kriz\/learning-features-2009-TR.pdf"},{"key":"1191_CR18","first-page":"135","volume":"39","author":"JD Lambert","year":"1991","unstructured":"Lambert JD (1991) Numerical methods for ordinary differential equations. J Comput Appl Math 39:135\u2013148","journal-title":"J Comput Appl Math"},{"issue":"11","key":"1191_CR19","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"1191_CR20","unstructured":"Loshchilov I, Hutter F (2019) Decoupled weight decay regularization. In: International conference on learning representations (ICLR)"},{"key":"1191_CR21","doi-asserted-by":"publisher","DOI":"10.1002\/jts.70033","author":"Z Mamat","year":"2025","unstructured":"Mamat Z, Mathersul DC, Bayley PJ (2025) Cognition improvement in US veterans undergoing treatment for posttraumatic stress disorder: secondary analyses from a randomized controlled trial. J Trauma Stress. https:\/\/doi.org\/10.1002\/jts.70033","journal-title":"J Trauma Stress"},{"key":"1191_CR22","doi-asserted-by":"publisher","unstructured":"Monti MM (2025) Is cognitive motor dissociation just a minimally conscious state \u201cplus\u201d by another name? medRxiv. https:\/\/doi.org\/10.1101\/2025.06.11.25329346","DOI":"10.1101\/2025.06.11.25329346"},{"key":"1191_CR23","first-page":"372","volume":"27","author":"Y Nesterov","year":"1983","unstructured":"Nesterov Y (1983) A method for solving the convex programming problem with convergence rate $$o(1\/k^2)$$. Sov Math Dokl 27:372\u2013376","journal-title":"Sov Math Dokl"},{"key":"1191_CR24","volume-title":"Numerical optimization","author":"J Nocedal","year":"2006","unstructured":"Nocedal J, Wright SJ (2006) Numerical optimization. Springer, Berlin"},{"key":"1191_CR25","doi-asserted-by":"publisher","unstructured":"Nurujjaman MD (2020) Enhanced Euler\u2019s method to solve first order ordinary differential equations with better accuracy. https:\/\/doi.org\/10.5281\/zenodo.3731020","DOI":"10.5281\/zenodo.3731020"},{"key":"1191_CR26","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. In: NeurIPS Autodiff Workshop"},{"issue":"5","key":"1191_CR27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/0041-5553(64)90137-5","volume":"4","author":"BT Polyak","year":"1964","unstructured":"Polyak BT (1964) Some methods of speeding up the convergence of iteration methods. USSR Comput Math Math Phys 4(5):1\u201317","journal-title":"USSR Comput Math Math Phys"},{"issue":"1","key":"1191_CR28","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/S0893-6080(98)00116-6","volume":"12","author":"N Qian","year":"1999","unstructured":"Qian N (1999) On the momentum term in gradient descent learning algorithms. Neural Netw 12(1):145\u2013151. https:\/\/doi.org\/10.1016\/S0893-6080(98)00116-6","journal-title":"Neural Netw"},{"key":"1191_CR29","unstructured":"Reddi SJ, Kale S, Kumar S (2018) On the convergence of Adam and beyond. arXiv:1904.09237"},{"issue":"3","key":"1191_CR30","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins H, Monro S (1951) A stochastic approximation method. Ann Math Stat 22(3):400\u2013407","journal-title":"Ann Math Stat"},{"issue":"6088","key":"1191_CR31","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","volume":"323","author":"DE Rumelhart","year":"1986","unstructured":"Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323(6088):533\u2013536","journal-title":"Nature"},{"key":"1191_CR32","unstructured":"Sutskever I, Martens J, Dahl G, Hinton G (2013) On the importance of initialization and momentum in deep learning. In: International conference on machine learning, pp 1139\u20131147"},{"key":"1191_CR33","unstructured":"Tan M, Le QV (2019) EfficientNet: rethinking model scaling for convolutional neural networks. In: International conference on machine learning. PMLR, pp 6105\u20136114"},{"key":"1191_CR34","unstructured":"Tieleman T, Hinton G (2012) Lecture $$6.5$$-rmsprop. In: COURSERA: neural networks for machine learning"},{"key":"1191_CR35","first-page":"4148","volume":"30","author":"AC Wilson","year":"2017","unstructured":"Wilson AC, Roelofs R, Stern M, Srebro N, Recht B (2017) The marginal value of adaptive gradient methods in machine learning. Adv Neural Inform Proc Syst (NeurIPS) 30:4148\u20134158","journal-title":"Adv Neural Inform Proc Syst (NeurIPS)"},{"key":"1191_CR36","unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747"},{"key":"1191_CR37","unstructured":"Zaheer M, Reddi SJ, Kale S, Kumar S (2018) YOGI: scaling adaptive methods for large batch training. arXiv:1802.01588"},{"key":"1191_CR38","unstructured":"Zaheer M, Reddi SJ, Sachan D, Kale S, Kumar S (2018) Adaptive methods for nonconvex optimization. In: Advances in neural information processing systems (NeurIPS),\u00a031. https:\/\/papers.nips.cc\/paper_files\/paper\/2018\/hash\/90365351ccc7437a1309dc64e4db32a3-Abstract.html"},{"key":"1191_CR39","unstructured":"Zeiler MD (2013) ADADELTA: an adaptive learning rate method. In: International conference on learning representations (ICLR). arXiv:1212.5701"}],"container-title":["Evolutionary Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12065-026-01191-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12065-026-01191-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12065-026-01191-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:43:20Z","timestamp":1776750200000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12065-026-01191-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,21]]},"references-count":39,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["1191"],"URL":"https:\/\/doi.org\/10.1007\/s12065-026-01191-6","relation":{},"ISSN":["1864-5909","1864-5917"],"issn-type":[{"value":"1864-5909","type":"print"},{"value":"1864-5917","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,21]]},"assertion":[{"value":"6 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 April 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 April 2026","order":4,"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 no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"75"}}