{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T06:26:37Z","timestamp":1785392797068,"version":"3.55.0"},"reference-count":76,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2020,7,6]],"date-time":"2020-07-06T00:00:00Z","timestamp":1593993600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,7,6]],"date-time":"2020-07-06T00:00:00Z","timestamp":1593993600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100010198","name":"Ministerio de Econom\u00eda, Industria y Competitividad, Gobierno de Espa\u00f1a","doi-asserted-by":"publisher","award":["TRA2016-76914-C3-2-"],"award-info":[{"award-number":["TRA2016-76914-C3-2-"]}],"id":[{"id":"10.13039\/501100010198","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2021,4]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The backpropagation (BP) algorithm is a gradient-based algorithm used for training a feedforward neural network (FNN). Despite the fact that BP is still used today when FNNs are trained, it has some disadvantages, including the following: (i) it fails when non-differentiable functions are addressed, (ii) it can become trapped in local minima, and (iii) it has slow convergence. In order to solve some of these problems, metaheuristic algorithms have been used to train FNN. Although they have good exploration skills, they are not as good as gradient-based algorithms at exploitation tasks. The main contribution of this article lies in its application of novel memetic approaches based on the Gravitational Search Algorithm (GSA) and Chaotic Gravitational Search Algorithm (CGSA) algorithms, called respectively Memetic Gravitational Search Algorithm (MGSA) and Memetic Chaotic Gravitational Search Algorithm (MCGSA), to train FNNs in three classical benchmark problems: the XOR problem, the approximation of a continuous function, and classification tasks. The results show that both approaches constitute suitable alternatives for training FNNs, even improving on the performance of other state-of-the-art metaheuristic algorithms such as ParticleSwarm Optimization (PSO), the Genetic Algorithm (GA), the Adaptive Differential Evolution algorithm with Repaired crossover rate (Rcr-JADE), and the Covariance matrix learning and Bimodal distribution parameter setting Differential Evolution (COBIDE) algorithm. Swarm optimization, the genetic algorithm, the adaptive differential evolution algorithm with repaired crossover rate, and the covariance matrix learning and bimodal distribution parameter setting differential evolution algorithm.<\/jats:p>","DOI":"10.1007\/s00521-020-05131-y","type":"journal-article","created":{"date-parts":[[2020,7,6]],"date-time":"2020-07-06T14:03:36Z","timestamp":1594044216000},"page":"2561-2588","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Memetic algorithms for training feedforward neural networks: an approach based on gravitational search algorithm"],"prefix":"10.1007","volume":"33","author":[{"given":"Ricardo","family":"Garc\u00eda-R\u00f3denas","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luis Jimenez","family":"Linares","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6291-6637","authenticated-orcid":false,"given":"Julio Alberto","family":"L\u00f3pez-G\u00f3mez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,7,6]]},"reference":[{"issue":"1","key":"5131_CR1","doi-asserted-by":"crossref","first-page":"334","DOI":"10.1016\/j.ijepes.2012.10.047","volume":"46","author":"SM Abd-Elazim","year":"2013","unstructured":"Abd-Elazim SM, Ali ES (2013) A hybrid particle swarm optimization and bacterial foraging for optimal power system stabilizers design. Int J Electr Power Energy Syst 46(1):334\u2013341","journal-title":"Int J Electr Power Energy Syst"},{"key":"5131_CR2","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.ijepes.2016.02.023","volume":"82","author":"SM Abd Elazim","year":"2016","unstructured":"Abd Elazim SM, Ali ES (2016) Optimal SSSC design for damping power systems oscillations via gravitational search algorithm. Int J Electr Power Energy Syst 82:161\u2013168","journal-title":"Int J Electr Power Energy Syst"},{"issue":"6","key":"5131_CR3","first-page":"1575","volume":"13","author":"N Aldhafferi","year":"2018","unstructured":"Aldhafferi N, Owolabi TO, Akande KO, Olatunji SO, Alqahtani A (2018) Development of hybrid computational intelligence model for estimating relative cooling power of manganite-based materials for magnetic refrigeration enhancement. J Eng Appl Sci 13(6):1575\u20131583","journal-title":"J Eng Appl Sci"},{"key":"5131_CR4","unstructured":"Arora, S., Cohen, N., Golowich, N., Hu, W.: A convergence analysis of gradient descent for deep linear neural networks. CoRR abs\/1810.0 (2018)"},{"issue":"1","key":"5131_CR5","doi-asserted-by":"crossref","first-page":"88","DOI":"10.1007\/s10489-015-0686-6","volume":"44","author":"S Azali","year":"2016","unstructured":"Azali S, Sheikhan M (2016) Intelligent control of photovoltaic system using BPSO-GSA-optimized neural network and fuzzy-based PID for maximum power point tracking. Appl Intell 44(1):88\u2013110","journal-title":"Appl Intell"},{"issue":"20","key":"5131_CR6","doi-asserted-by":"crossref","first-page":"7046","DOI":"10.1016\/j.eswa.2015.05.013","volume":"42","author":"M Ballings","year":"2015","unstructured":"Ballings M, Van Den Poel D, Hespeels N, Gryp R (2015) Evaluating multiple classifiers for stock price direction prediction. Exp Syst Appl 42(20):7046\u20137056","journal-title":"Exp Syst Appl"},{"issue":"1\u20134","key":"5131_CR7","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1016\/S0925-2312(01)00658-0","volume":"48","author":"S Bohte","year":"2002","unstructured":"Bohte S, Kok J, La Poutr\u00e9 H (2002) Error-backpropagation in temporally encoded networks of spiking neurons. Neurocomputing 48(1\u20134):17\u201337","journal-title":"Neurocomputing"},{"issue":"4","key":"5131_CR8","doi-asserted-by":"crossref","first-page":"1769","DOI":"10.1109\/TMAG.2007.892515","volume":"43","author":"T Chady","year":"2007","unstructured":"Chady T, Lopato P (2007) Flaws identification using an approximation function and artificial neural networks. IEEE Trans Magn 43(4):1769\u20131772","journal-title":"IEEE Trans Magn"},{"key":"5131_CR9","doi-asserted-by":"crossref","first-page":"1152","DOI":"10.1007\/11539902_145","volume-title":"Advances in natural computation","author":"CT Cheng","year":"2005","unstructured":"Cheng CT, Lin JY, Sun YG, Chau K (2005) Long-term prediction of discharges in Manwan hydropower using adaptive-network-based fuzzy inference systems models. In: Wang L, Chen K, Ong YS (eds) Advances in natural computation. Springer, Berlin, pp 1152\u20131161"},{"key":"5131_CR10","unstructured":"Dennis, J.E., Mor\u00e9, J.J.: Quasi-Newton Methods, Motivation and Theory (1974)"},{"issue":"1","key":"5131_CR11","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.ins.2014.06.009","volume":"289","author":"J Derrac","year":"2014","unstructured":"Derrac J, Garc\u00eda S, Hui S, Suganthan P, Herrera F (2014) Analyzing convergence performance of evolutionary algorithms: a statistical approach. Inf Sci 289(1):41\u201358","journal-title":"Inf Sci"},{"key":"5131_CR12","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/978-3-642-32063-7_22","volume-title":"Intelligent informatics","author":"H Dhahri","year":"2013","unstructured":"Dhahri H, Alimi AM, Abraham A (2013) Hierarchical particle swarm optimization for the design of beta basis function neural network. In: Abraham A, Thampi SM (eds) Intelligent informatics. Springer, Berlin, pp 193\u2013205"},{"issue":"7","key":"5131_CR13","doi-asserted-by":"crossref","first-page":"1074","DOI":"10.1109\/TNNLS.2013.2251001","volume":"24","author":"M El-Melegy","year":"2013","unstructured":"El-Melegy M (2013) Random sampler m-estimator algorithm with sequential probability ratio test for robust function approximation via feed-forward neural networks. IEEE Trans Neural Netw Learn Syst 24(7):1074\u20131085","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"3","key":"5131_CR14","doi-asserted-by":"crossref","first-page":"772","DOI":"10.1016\/j.ejor.2015.05.052","volume":"246","author":"J Espinosa-Aranda","year":"2015","unstructured":"Espinosa-Aranda J, Garc\u00eda-R\u00f3denas R, Ram\u00edrez-Flores M, L\u00f3pez-Garc\u00eda M, Angulo E (2015) High-speed railway scheduling based on user preferences. Eur J Oper Res 246(3):772\u2013786","journal-title":"Eur J Oper Res"},{"key":"5131_CR15","first-page":"524","volume-title":"Advances in neural information processing systems 2. chap. The Cascad","author":"SE Fahlman","year":"1990","unstructured":"Fahlman SE, Lebiere C (1990) Advances in neural information processing systems 2. chap. The Cascad. Morgan Kaufmann Publishers Inc, San Francisco, pp 524\u2013532"},{"key":"5131_CR16","first-page":"3133","volume":"15","author":"M Fern\u00e1ndez-Delgado","year":"2014","unstructured":"Fern\u00e1ndez-Delgado M, Cernadas E, Barro S, Amorim D (2014) Do we need hundreds of classifiers to solve real world classification problems? J Mach Learn Res 15:3133\u20133181","journal-title":"J Mach Learn Res"},{"issue":"1","key":"5131_CR17","first-page":"411","volume":"12","author":"F Fotovatikhah","year":"2018","unstructured":"Fotovatikhah F, Herrera M, Shamshirband S, Chau KW, Ardabili SF, Piran MJ (2018) Survey of computational intelligence as basis to big flood management: challenges, research directions and future work. Eng Appl Comput Fluid Mech 12(1):411\u2013437","journal-title":"Eng Appl Comput Fluid Mech"},{"key":"5131_CR18","doi-asserted-by":"crossref","first-page":"2044","DOI":"10.1016\/j.ins.2009.12.010","volume":"180","author":"S Garc\u00eda","year":"2010","unstructured":"Garc\u00eda S, Fern\u00e1ndez A, Luengo J, Herrera F (2010) Advanced nonparametric tests for multiple comparisons in the design of experiments in computational intelligence and data mining: experimental analysis of power. Inf Sci 180:2044\u20132064","journal-title":"Inf Sci"},{"key":"5131_CR19","volume-title":"On the performance of classic and deep neural models in image recognition","author":"R Garc\u00eda-R\u00f3denas","year":"2017","unstructured":"Garc\u00eda-R\u00f3denas R, Linares L, L\u00f3pez-G\u00f3mez J (2017) On the performance of classic and deep neural models in image recognition, vol 10585. LNCS, Berlin"},{"key":"5131_CR20","doi-asserted-by":"crossref","unstructured":"Garc\u00eda-R\u00f3denas R, Linares LJ, L\u00f3pez-G\u00f3mez JA (2019) A memetic chaotic gravitational search algorithm for unconstrained global optimization problems. Appl Soft Comput","DOI":"10.1016\/j.asoc.2019.03.011"},{"issue":"2","key":"5131_CR21","doi-asserted-by":"crossref","first-page":"113","DOI":"10.1016\/0165-1684(84)90013-6","volume":"6","author":"WA Gardner","year":"1984","unstructured":"Gardner WA (1984) Learning characteristics of stochastic-gradient-descent algorithms: a general study, analysis, and critique. Signal Process 6(2):113\u2013133","journal-title":"Signal Process"},{"issue":"10","key":"5131_CR22","doi-asserted-by":"crossref","first-page":"1419","DOI":"10.1016\/j.neunet.2009.04.003","volume":"22","author":"S Ghosh-Dastidar","year":"2009","unstructured":"Ghosh-Dastidar S, Adeli H (2009) A new supervised learning algorithm for multiple spiking neural networks with application in epilepsy and seizure detection. Neural Netw 22(10):1419\u20131431","journal-title":"Neural Netw"},{"key":"5131_CR23","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: In Proceedings of the international conference on artificial intelligence and statistics (AISTATS\u201910). Society for Artificial Intelligence and Statistics (2010)"},{"key":"5131_CR24","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1016\/j.asoc.2013.11.005","volume":"15","author":"W Gong","year":"2014","unstructured":"Gong W, Cai Z, Wang Y (2014) Repairing the crossover rate in adaptive differential evolution. Appl Soft Comput J 15:149\u2013168","journal-title":"Appl Soft Comput J"},{"issue":"24","key":"5131_CR25","doi-asserted-by":"crossref","first-page":"5364","DOI":"10.1016\/j.ins.2011.07.049","volume":"181","author":"W Gong","year":"2011","unstructured":"Gong W, Fialho A, Cai Z, Li H (2011) Adaptive strategy selection in differential evolution for numerical optimization: an empirical study. Inf Sci 181(24):5364\u20135386","journal-title":"Inf Sci"},{"issue":"1","key":"5131_CR26","doi-asserted-by":"crossref","first-page":"76","DOI":"10.1109\/34.107014","volume":"14","author":"M Gori","year":"1992","unstructured":"Gori M, Tesi A (1992) On the problem of local minima in backpropagation. IEEE Trans Pattern Anal Mach Intell 14(1):76\u201386","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5131_CR27","doi-asserted-by":"crossref","unstructured":"Guo SM, Tsai JH, Yang CC, Hsu PH (2015) A self-optimization approach for L-SHADE incorporated with eigenvector-based crossover and successful-parent-selecting framework on CEC 2015 benchmark set. In: 2015 IEEE congress on evolutionary computation, CEC 2015\u2014Proceedings, pp 1003\u20131010","DOI":"10.1109\/CEC.2015.7256999"},{"key":"5131_CR28","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1016\/j.eswa.2017.01.057","volume":"78","author":"J Hagenauer","year":"2017","unstructured":"Hagenauer J, Helbich M (2017) A comparative study of machine learning classifiers for modeling travel mode choice. Expert Syst Appl 78:273\u2013282","journal-title":"Expert Syst Appl"},{"key":"5131_CR29","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1016\/j.neucom.2018.07.080","volume":"335","author":"F Han","year":"2018","unstructured":"Han F, Jiang J, Ling QH, Su BY (2018) A survey on metaheuristic optimization for random single-hidden layer feedforward neural network. Neurocomputing 335:261\u2013273","journal-title":"Neurocomputing"},{"issue":"5786","key":"5131_CR30","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504\u2013507","journal-title":"Science"},{"issue":"5","key":"5131_CR31","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","volume":"2","author":"K Hornik","year":"1989","unstructured":"Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359\u2013366","journal-title":"Neural Netw"},{"issue":"1","key":"5131_CR32","doi-asserted-by":"crossref","first-page":"8","DOI":"10.1109\/79.180705","volume":"10","author":"DR Hush","year":"1993","unstructured":"Hush DR, Horne BG (1993) Progress in supervised neural networks. IEEE Signal Process Mag 10(1):8\u201339","journal-title":"IEEE Signal Process Mag"},{"key":"5131_CR33","doi-asserted-by":"crossref","unstructured":"Irie M (1988) Capabilities of three-layered perceptrons. In: IEEE 1988 international conference on neural networks, pp 641\u2013648","DOI":"10.1109\/ICNN.1988.23901"},{"issue":"2","key":"5131_CR34","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1109\/TSMCB.2003.818557","volume":"34","author":"CF Juang","year":"2004","unstructured":"Juang CF (2004) A hybrid of genetic algorithm and particle swarm optimization for recurrent network design. IEEE Trans Syst Man Cybern B (Cybern) 34(2):997\u20131006","journal-title":"IEEE Trans Syst Man Cybern B (Cybern)"},{"issue":"1","key":"5131_CR35","first-page":"108","volume":"214","author":"D Karaboga","year":"2009","unstructured":"Karaboga D, Akay B (2009) A comparative study of artificial bee colony algorithm. Appl Math Comput 214(1):108\u2013132","journal-title":"Appl Math Comput"},{"key":"5131_CR36","doi-asserted-by":"crossref","first-page":"1060","DOI":"10.1016\/j.ijepes.2015.07.016","volume":"73","author":"RK Khadanga","year":"2015","unstructured":"Khadanga RK, Satapathy JK (2015) A new hybrid GA-GSA algorithm for tuning damping controller parameters for a unified power flow controller. Int J Electr Power Energy Syst 73:1060\u20131069","journal-title":"Int J Electr Power Energy Syst"},{"key":"5131_CR37","first-page":"1","volume":"10","author":"H Larochelle","year":"2009","unstructured":"Larochelle H, Bengio Y, Louradour J, Lamblin P (2009) Exploring strategies for training deep neural networks. J Mach Learn Res 10:1\u201340","journal-title":"J Mach Learn Res"},{"key":"5131_CR38","doi-asserted-by":"crossref","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Nature 521","DOI":"10.1038\/nature14539"},{"issue":"1","key":"5131_CR39","first-page":"503","volume":"45","author":"DC Liu","year":"1989","unstructured":"Liu DC, Nocedal J (1989) On the limited memory BFGS method for large scale optimization. Math Program 45(1):503\u2013528","journal-title":"Math Program"},{"issue":"P1","key":"5131_CR40","doi-asserted-by":"crossref","first-page":"231","DOI":"10.1016\/j.neucom.2014.09.048","volume":"151","author":"M Garc\u00eda Luz L\u00f3pez","year":"2015","unstructured":"Garc\u00eda Luz L\u00f3pez M, Garc\u00eda-R\u00f3denas R, Gonz\u00e1lez G\u00f3mez A (2015) K-means algorithms for functional data. Neurocomputing 151(P1):231\u2013245","journal-title":"Neurocomputing"},{"issue":"1","key":"5131_CR41","first-page":"27","volume":"90","author":"B Malakooti","year":"1998","unstructured":"Malakooti B, Zhou Y (1998) Approximating polynomial functions by feedforward artificial neural networks: capacity analysis and design. Appl Math Comput 90(1):27\u201351","journal-title":"Appl Math Comput"},{"issue":"1","key":"5131_CR42","doi-asserted-by":"crossref","first-page":"1457","DOI":"10.1016\/j.asoc.2010.04.017","volume":"11","author":"NA Mat Isa","year":"2011","unstructured":"Mat Isa NA, Mamat WMFW (2011) Clustered-hybrid multilayer perceptron network for pattern recognition application. Appl Soft Comput 11(1):1457\u20131466","journal-title":"Appl Soft Comput"},{"issue":"2\u20133","key":"5131_CR43","doi-asserted-by":"crossref","first-page":"427","DOI":"10.1016\/j.neunet.2007.12.031","volume":"21","author":"MA Mazurowski","year":"2008","unstructured":"Mazurowski MA, Habas PA, Zurada JM, Lo JY, Baker JA, Tourassi GD (2008) Training neural network classifiers for medical decision making: the effects of imbalanced datasets on classification performance. Neural Netw 21(2\u20133):427\u2013436","journal-title":"Neural Netw"},{"key":"5131_CR44","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1016\/j.asoc.2017.01.008","volume":"53","author":"S Mirjalili","year":"2017","unstructured":"Mirjalili S, Gandomi A (2017) Chaotic gravitational constants for the gravitational search algorithm. Appl Soft Comput J 53:407\u2013419","journal-title":"Appl Soft Comput J"},{"issue":"22","key":"5131_CR45","first-page":"11125","volume":"218","author":"S Mirjalili","year":"2012","unstructured":"Mirjalili S, Mohd Hashim S, Moradian Sardroudi H (2012) Training feedforward neural networks using hybrid particle swarm optimization and gravitational search algorithm. Appl Math Comput 218(22):11125\u201311137","journal-title":"Appl Math Comput"},{"issue":"1","key":"5131_CR46","first-page":"584","volume":"12","author":"R Moazenzadeh","year":"2018","unstructured":"Moazenzadeh R, Mohammadi B, Shamshirband S, Chau KW (2018) Coupling a firefly algorithm with support vector regression to predict evaporation in northern Iran. Eng Appl Comput Fluid Mech 12(1):584\u2013597","journal-title":"Eng Appl Comput Fluid Mech"},{"key":"5131_CR47","first-page":"219","volume-title":"New ideas in optimization, chap. Memetic Al","author":"P Moscato","year":"1999","unstructured":"Moscato P (1999) New ideas in optimization, chap. Memetic Al. McGraw-Hill Ltd., Maidenhead, pp 219\u2013234"},{"issue":"1","key":"5131_CR48","first-page":"611","volume":"12","author":"B Najafi","year":"2018","unstructured":"Najafi B, Ardabili SF, Shamshirband S, Chau KW, Rabczuk T (2018) Application of ANNs, ANFIS and RSM to estimating and optimizing the parameters that affect the yield and cost of biodiesel production. Eng Appl Comput Fluid Mech 12(1):611\u2013624","journal-title":"Eng Appl Comput Fluid Mech"},{"key":"5131_CR49","doi-asserted-by":"crossref","unstructured":"Najafzadeh M, Azamathulla HM (2015) Neuro-fuzzy GMDH to predict the scour pile groups due to waves. J Comput Civil Eng 29(5)","DOI":"10.1061\/(ASCE)CP.1943-5487.0000376"},{"key":"5131_CR50","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.swevo.2011.11.003","volume":"2","author":"F Neri","year":"2012","unstructured":"Neri F, Cotta C (2012) Memetic algorithms and memetic computing optimization: a literature review. Swarm Evolut Comput 2:1\u201314","journal-title":"Swarm Evolut Comput"},{"issue":"151","key":"5131_CR51","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1090\/S0025-5718-1980-0572855-7","volume":"35","author":"J Nocedal","year":"1980","unstructured":"Nocedal J (1980) Updating quasi-Newton matrices with limited storage. Math Comput 35(151):773\u2013782","journal-title":"Math Comput"},{"key":"5131_CR52","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.engappai.2017.01.013","volume":"60","author":"VK Ojha","year":"2017","unstructured":"Ojha VK, Abraham A, Sn\u00e1\u0161el V (2017) Metaheuristic design of feedforward neural networks: a review of two decades of research. Eng Appl Artif Intell 60:97\u2013116","journal-title":"Eng Appl Artif Intell"},{"key":"5131_CR53","doi-asserted-by":"crossref","unstructured":"Ojha VK, Abraham A, Sn\u00e1\u0161el V (2014) Simultaneous optimization of neural network weights and active nodes using metaheuristics. In: 2014 14th international conference on hybrid intelligent systems, pp 248\u2013253","DOI":"10.1109\/HIS.2014.7086207"},{"key":"5131_CR54","doi-asserted-by":"crossref","unstructured":"Omrani H (2015) Predicting travel mode of individuals by machine learning. In: Transportation research procedia, vol\u00a010. Elsevier, Amsterdam, pp 840\u2013849","DOI":"10.1016\/j.trpro.2015.09.037"},{"key":"5131_CR55","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.commatsci.2017.05.047","volume":"137","author":"TO Owolabi","year":"2017","unstructured":"Owolabi TO, Gondal MA (2017) A hybrid intelligent scheme for estimating band gap of doped titanium dioxide semiconductor using crystal lattice distortion. Comput Mater Sci 137:249\u2013256","journal-title":"Comput Mater Sci"},{"key":"5131_CR56","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.aca.2018.05.029","volume":"1030","author":"TO Owolabi","year":"2018","unstructured":"Owolabi TO, Gondal MA (2018) Development of hybrid extreme learning machine based chemo-metrics for precise quantitative analysis of LIBS spectra using internal reference pre-processing method. Anal Chim Acta 1030:33\u201341","journal-title":"Anal Chim Acta"},{"key":"5131_CR57","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1016\/j.ins.2016.12.028","volume":"384","author":"A Piotrowski","year":"2017","unstructured":"Piotrowski A, Napiorkowski M, Napiorkowski J, Rowinski P (2017) Swarm intelligence and evolutionary algorithms: performance versus speed. Inf Sci 384:34\u201385","journal-title":"Inf Sci"},{"key":"5131_CR58","doi-asserted-by":"crossref","unstructured":"Po\u0161\u00edk P, Huyer W, P\u00e1l L (2012) A comparison of global search algorithms for continuous black-box optimization. In: Evolutionary computation, 20","DOI":"10.1162\/EVCO_a_00084"},{"issue":"1","key":"5131_CR59","first-page":"57","volume":"8","author":"P Prisecaru","year":"2016","unstructured":"Prisecaru P (2016) Challenges of the fourth industrial revolution. Knowl Horizons Econ 8(1):57\u201362","journal-title":"Knowl Horizons Econ"},{"issue":"13","key":"5131_CR60","doi-asserted-by":"crossref","first-page":"2232","DOI":"10.1016\/j.ins.2009.03.004","volume":"179","author":"E Rashedi","year":"2009","unstructured":"Rashedi E, Nezamabadi-pour H, Saryazdi S (2009) GSA: a gravitational search algorithm. Inf Sci 179(13):2232\u20132248","journal-title":"Inf Sci"},{"key":"5131_CR61","unstructured":"Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In: IEEE international conference on neural networks, pp 586\u2013591 (1993)"},{"key":"5131_CR62","doi-asserted-by":"crossref","unstructured":"Sheikhpour S, Sabouri M, Zahiri SH (2013) A hybrid gravitational search algorithm genetic algorithm for neural network training. In: 2013 21st Iranian conference on electrical engineering, ICEE 2013","DOI":"10.1109\/IranianCEE.2013.6599894"},{"key":"5131_CR63","doi-asserted-by":"crossref","unstructured":"Silva P, Fernandes E, Neto A (2002) A feed forward neural network with resolution properties for function approximation and modeling. In: Proceedings-Brazilian symposium on neural networks, SBRN, vol 2002-Jan, pp 55\u201360","DOI":"10.1109\/SBRN.2002.1181435"},{"key":"5131_CR64","doi-asserted-by":"crossref","unstructured":"Tanabe R, Fukunaga A (2013) Success-history based parameter adaptation for differential evolution. In: 2013 IEEE congress on evolutionary computation, CEC 2013, pp 71\u201378","DOI":"10.1109\/CEC.2013.6557555"},{"issue":"1","key":"5131_CR65","doi-asserted-by":"crossref","first-page":"69","DOI":"10.1109\/TNN.2005.860885","volume":"17","author":"JT Tsai","year":"2006","unstructured":"Tsai JT, Chou JH, Liu TK (2006) Tuning the structure and parameters of a neural network by using hybrid Taguchi-genetic algorithm. IEEE Trans Neural Netw 17(1):69\u201380","journal-title":"IEEE Trans Neural Netw"},{"key":"5131_CR66","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1137\/0111030","volume":"11","author":"DW Marquardt","year":"1963","unstructured":"Marquardt DW (1963) An algorithm for least square estimation of non-linear parameters. SIAM J Appl Math 11:431\u2013441","journal-title":"SIAM J Appl Math"},{"issue":"8","key":"5131_CR67","doi-asserted-by":"crossref","first-page":"5711","DOI":"10.3390\/e17085711","volume":"17","author":"S Wang","year":"2015","unstructured":"Wang S, Zhang Y, Ji G, Yang J, Wu J, Wei L (2015) Fruit classification by wavelet-entropy and feedforward neural network trained by fitness-scaled chaotic abc and biogeography-based optimization. Entropy 17(8):5711\u20135728","journal-title":"Entropy"},{"key":"5131_CR68","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.envres.2015.02.002","volume":"139","author":"Wang Wc","year":"2015","unstructured":"Wc Wang, Kw Chau, Qiu L, Yb Chen (2015) Improving forecasting accuracy of medium and long-term runoff using artificial neural network based on EEMD decomposition. Environ Res 139:46\u201354","journal-title":"Environ Res"},{"key":"5131_CR69","doi-asserted-by":"crossref","first-page":"232","DOI":"10.1016\/j.asoc.2014.01.038","volume":"18","author":"Y Wang","year":"2014","unstructured":"Wang Y, Li HX, Huang T, Li L (2014) Differential evolution based on covariance matrix learning and bimodal distribution parameter setting. Appl Soft Comput J 18:232\u2013247","journal-title":"Appl Soft Comput J"},{"issue":"1","key":"5131_CR70","doi-asserted-by":"crossref","first-page":"293","DOI":"10.1016\/j.engappai.2012.01.023","volume":"26","author":"M Yaghini","year":"2013","unstructured":"Yaghini M, Khoshraftar MM, Fallahi M (2013) A hybrid algorithm for artificial neural network training. Eng Appl Artif Intell 26(1):293\u2013301","journal-title":"Eng Appl Artif Intell"},{"issue":"4","key":"5131_CR71","doi-asserted-by":"crossref","first-page":"539","DOI":"10.1002\/int.4550080406","volume":"8","author":"X Yao","year":"1993","unstructured":"Yao X (1993) A review of evolutionary artificial neural networks. Int J Intell Syst 8(4):539\u2013567","journal-title":"Int J Intell Syst"},{"key":"5131_CR72","doi-asserted-by":"crossref","first-page":"387","DOI":"10.1016\/j.jhydrol.2018.11.069","volume":"569","author":"ZM Yaseen","year":"2019","unstructured":"Yaseen ZM, Sulaiman SO, Deo RC, Chau KW (2019) An enhanced extreme learning machine model for river flow forecasting: state-of-the-art, practical applications in water resource engineering area and future research direction. J Hydrol 569:387\u2013408","journal-title":"J Hydrol"},{"issue":"6","key":"5131_CR73","doi-asserted-by":"crossref","first-page":"3457","DOI":"10.1016\/j.matdes.2011.01.058","volume":"32","author":"F Yin","year":"2011","unstructured":"Yin F, Mao H, Hua L (2011) A hybrid of back propagation neural network and genetic algorithm for optimization of injection molding process parameters. Mater Design 32(6):3457\u20133464","journal-title":"Mater Design"},{"issue":"6","key":"5131_CR74","first-page":"333","volume":"7","author":"Z Zainuddin","year":"2008","unstructured":"Zainuddin Z, Ong P (2008) Function approximation using artificial neural networks. WSEAS Trans Math 7(6):333\u2013338","journal-title":"WSEAS Trans Math"},{"issue":"2","key":"5131_CR75","first-page":"1026","volume":"185","author":"JR Zhang","year":"2007","unstructured":"Zhang JR, Zhang J, Lok TM, Lyu MR (2007) A hybrid particle swarm optimization-back-propagation algorithm for feedforward neural network training. Appl Math Comput 185(2):1026\u20131037","journal-title":"Appl Math Comput"},{"key":"5131_CR76","volume-title":"Understanding big data: analytics for enterprise class hadoop and streaming data","author":"P Zikopoulos","year":"2011","unstructured":"Zikopoulos P, Eaton C (2011) Understanding big data: analytics for enterprise class hadoop and streaming data, 1st edn. McGraw-Hill, New York","edition":"1"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05131-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-020-05131-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-020-05131-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,7,5]],"date-time":"2021-07-05T19:50:58Z","timestamp":1625514658000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-020-05131-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,6]]},"references-count":76,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,4]]}},"alternative-id":["5131"],"URL":"https:\/\/doi.org\/10.1007\/s00521-020-05131-y","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,7,6]]},"assertion":[{"value":"12 July 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}