Abstract
The main goal of the current investigation is to answer some open questions regarding the applicability of bio-inspired techniques for simultaneous evolving and training of extreme learning machines (ELMs). Over the past decade, ELMs have successfully been applied to a wide range of regression and classification problems. However, in most of the reports, classical learning systems have been used for training ELMs which can result in cumbersome mathematical formulations and unstable solutions when handling large databases. Moreover, there is no guarantee for converging to global optimum solutions when traditional methods are used for the regularized learning of ELMs, especially when the variables in the database are correlated. To cope with such flaws, some researchers have used bio-inspired computation (BIC) for the topology evolving and parameter tuning of ELMs. However, the research stream still experiences its infancy. In an attempt to take a significant stride towards fulfilling the existing gap, the authors conduct a comprehensive analysis by adopting different BIC and classical methods for training ELMs. Based on the simulation results, some recommendations are given to guide researchers on using appropriate BICs for ELM training for small-scale, medium-scale, large-scale and very large-scale regression and classification problems.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig1_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig2_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig3_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig4_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig5_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig6_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig7_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig8_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig9_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig10_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig11_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig12_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig13_HTML.gif)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs10462-016-9461-2/MediaObjects/10462_2016_9461_Fig14_HTML.gif)
Similar content being viewed by others
References
Alexandre E, Cuadra L, Nieto-Borge JC, Candil-Garcia G, Del-Pino M, Salcedo-Sanz S (2015) A hybrid genetic algorithm-extreme learning machine approach for accurate significant wave height reconstruction. Ocean Model 92:115–123
An J, Kang Q, Wang L, Wu Q (2013) Mussels wandering optimization: an ecologically inspired algorithm for global optimization. Cogn Comput 5:188–199
Azad NL, Mozaffari A, Hedrick K (2015) A hybrid switching predictive controller based on bi-level kernel-based ELM and online trajectory builder for automotive coldstart emissions reduction. Neurocomputing. doi:10.1016/j.neucom.2015.08.070
Bartlett PL (1998) The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network. IEEE Trans Inf Theory 44(2):525–536
Bazi Y, Alajlan N, Melgani F, AlHichri H, Malek S, Yager RR (2014) Differential evolution extreme learning machine for the classification of hyperspectral images. IEEE Geosci Remote Sens Lett 11(6):1066–1070
Cambria E, Huang GB, Chamara KLL et al (2013) Extreme learning machines [trends and controversies]. IEEE Intell Syst 28(6):30–59
Cao JW, Lin ZP, Huang GB (2011) Composite function wavelet neural networks with differential evolution and extreme learning machine. Neural Process Lett 33(3):251–265
Cao J, Zhi** L, Huang GB (2012) Self-adaptive evolutionary extreme learning machine. Neural Process Lett 36:285–305
Chang Y, Li Y, Wang F (2007) Soft sensing modeling based on extreme learning machine for biochemical processes. J Syst Simul 19(23):5587–5590
Deng W, Zheng Q, Chen L (2009) Regularized extreme learning machine. In: IEEE symposium on computational intelligence and data mining, CIDM ’09, March 30th–April 2nd, pp 289–295
Ding S, Su C, Yu J et al (2011) An optimizing BP neural network algorithm based on genetic algorithm. Artif Intell Rev 36(2):153–162
Ding S, Xu L, Chunyang SuC et al (2012) An optimizing method of RBF neural network based on genetic algorithm. Neural Comput Appl 21(2):333–336
Ding S, Zhao H, Zhang Y, Xu Y, Xu X, Nie R (2013) Extreme learning machine: algorithm, theory and applications. Artif Intell Rev. doi:10.1007/s10462-013-9405-z
Diao R, Shen Q (2015) Nature inspired feature selection meta-heuristics. Artif Intell Rev 44:311–340
Engelbrecht AP (2015) Particle swarm optimization with crossover: a review and empirical analysis. Artif Intell Rev. doi:10.1007/s10462-015-9445-7
Esmin AAA, Coelho RA, Matwin S (2015) A review on particle swarm optimization algorithm and its variants to clustering high-dimensional data. Artif Intell Rev 44:23–45
Fathi A, Mozaffari A (2013) Identification of a dynamic model for shape memory alloy actuator using Hammerstein-Wiener gray box and mutable smart bee algorithm. Int J Intell Comput Cybern 6(4):328–357
Fathi A, Mozaffari A (2014) Modeling a shape memory alloy actuator using an evolvable recursive black-box and hybrid heuristic algorithms inspired based on the annual migration of salmons in nature. Appl Soft Comput 14:229–251
Frank A, Asuncion A (2010) UCI machine learning repository. http://archive.ics.uci.edu/ml
Furtuna R, Curteanu S, Leon F (2012) Multi-objective optimization of a stacked neural network using an evolutionary hyper-heuristic. Appl Soft Comput 12(1):133–144
Han F, Yao HF, Ling QH (2013) An improved evolutionary extreme learning machine based on particle swarm optimization. Neurocomputing 116:87–93
Hastie T, Tibshirani R, Friedman J (2011) The elements of statistical learning. Springer, New York
Huang GB, Zhu QY, Siew CK (2005) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501
Huang GB, Chen L (2008) Enhanced random search based incremental extreme learning machine. Neurocomputing 71(16–18):3460–3468
Huang GB, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2(2):107–122
Huang G, Huang GB, Song S, You K (2015a) Trends in extreme learning machines: a review. Neural Netw 61:32–48
Huang GB, Bai Z, Kasun LLC, Vong MC (2015b) Local receptive fields based extreme learning machine. IEEE Comput Intell Mag 10(2):18–29
Jordehi AR, Jasni J (2015) Particle swarm optimization for discrete optimization problems: a review. Artif Intell Rev 43(2):243–258
Karaboga D, Basturk B (2007) On the performance of artificial bee colony (ABC) algorithm. Appl Soft Comput 8:687–697
Kockanat S, Karaboga D (2015) The design of two-dimensional digital filters based on metaheuristic optimization algorithms: a review of the literature. Artif Intell Rev 44:265–287
Li X, Mao W, Jiang W (2014) Fast sparse approximation of extreme learning machine. Neurocomputing 128:96–103
Li S, Wang P, Goel L (2015) Short-term load forecasting by wavelet transform and evolutionary extreme learning machine. Electr Power Syst Res 122:96–103
Liao S, Feng C (2014) Meta-ELM: ELM with ELM hidden nodes. Neurocomputing 128:81–87
Liu N, Wang H (2013) Evolutionary extreme learning machine and its application to image analysis. J Signal Process Syst 73(1):73–81
Luo X, Chang X, Ban X (2015) Regression and classification using extreme learning machine based on \(L_{1}\)-norm and \(L_{2}\)-norm. Neurocomputing. doi:10.1016/j.neucom.2015.03.112
Marie-Sainte SL (2015) A survey of particle swarm optimization techniques for solving university examination timetabling problem. Artif Intell Rev. doi:10.1007/s10462-015-9437-7
Martinez JM, Escandell-Montero P, Soria-Olivas E, Martin-Guerrero JD, Magdalena-Benedito R, Gomez-Sanchis J (2011) Regularized extreme learning machine for regression problems. Neurocomputing 74:3716–3721
Miche Y, Eirola E, Bas P, Simula O, Jutten C, Lendasse A, Verleysen M (2010) Ensemble modeling with a constrained linear system of leave-one-out outputs. In: European symposium on artificial neural networks- computational intelligence and machine learning, Belgium, 28–30 April, pp 19–24
Miche Y, Sorjamaa A, Bas P, Simula O, Jutten C, lendasse A (2010b) OP-ELM: optimally pruned extreme learning machine. IEEE Trans Neural Netw 21(1):158–162
Miche Y, Heeswijk M, Bas P, Simula O, Lendasse A (2011) TROP-ELM: a double-regularized ELM using LARS and Tikhonov regularization. Neurocomputing 74(16):2413–2421
Michalewicz Z (1994) Genetic algorithms + data structures = evolution programs. Springer, New York
Mohapatra P, Chakravarty S, Dash PK (2015) An improved cuckoo search based extreme learning machine for medical data classification. Swarm Evol Comput 24:25–49
Mozaffari A, Fathi A, Behzadipour S (2012) The great salmon run: a novel bio-inspired algorithm for artificial system design and optimization. Int J Bio-Inspired Comput 4(5):286–301
Mozaffari A, Ramiar A, Fathi A (2013) Optimal design of classic Atkinson engine with dynamic specific heat using adaptive neuro-fuzzy inference system and mutable smart bee algorithm. Swarm Evol Comput 12:74–91
Mozaffari A, Azad NL (2014) Optimally pruned extreme learning machine with ensemble of regularization techniques and negative correlation penalty applied to automotive engine coldstart hydrocarbon emission identification. Neurocomputing 131:143–156
Mozaffari A, Azad NL, Emami M, Fathi A (2015) Mixed continuous/binary quantum-inspired learning system with non-negative least square optimisation for automated design of regularised ensemble extreme learning machines. Exp Theor Artif Intell. doi:10.1080/0952813X.2015.1020574
Neshat M, Sepidnam G, Sargolzaei M, Najaran Toosi A (2012) Artificial fish swarm algorithm: a survey of the state-of-the-art, hybridization, combinatorial and indicative applications. Artif Intell Rev. doi:10.1007/s10462-012-9342-2
Neri F, Tirronen V (2009) Scale factor local search in differential evolution. Memet Comput 1(2):153–171
Prakasam A, Savarimuthu N (2015) Metaheuristic algorithms and probabilistic behaviour: a comprehensive analysis of ant colony optimization and its variants. Artif Intell Rev. doi:10.1007/s10462-015-9441-y
Qu Y, Shang C, Wu W, Shen Q (2011) Evolutionary fuzzy extreme learning machine for mammographic risk analysis. Int J Fuzzy Syst 13(4):282–291
Rashedi E, Nezamabadipour H, Saryazdi S (2009) GSA: a gravitational search algorithm. Inf Sci 179(13):2232–2248
Schmidt M (2005) Least squares optimization with \(\text{ L }_{1}\)-norm regularization, CS542B Project Report, December
Shao Z, Er MJ, Wang N (2015) An effective semi-cross-validation model selection method for extreme learning machine with ridge regression. Neurocomputing 151:933–942
Silva DNG, Pacifico LDS, Ludermir TB (2011) An evolutionary extreme learning machine based on group search optimizer. In: IEEE Congress on Evolutionary Computation, pp 574–580
Storn R, Price K (1997) Differential evolution: a simple and efficient heuristic for global optimization over continuous spaces. J Glob Optim 11:341–459
Tang J, Deng C, Huang GB (2015) Extreme learning machine for multilayer perceptron. IEEE Trans Neural Netw Learn Syst. doi:10.1109/TNNLS.2015.2424995
Taormina R, Chau KW (2015) Data-driven input variable selection for rainfall-runoff modeling using binary-coded particle swarm optimization and extreme learning machines. J Hydrol. doi:10.1016/j.jhydrol.2015.08.022
Teoh CK, Wibowo A, Ngadiman MS (2015) Review of state of the art for metaheuristic techniques in academic scheduling problems. Artif Intell Rev 44:1–21
Wang D, Alhamdoosh M (2013) Evolutionary extreme learning machine ensembles with size control. Neurocomputing 102:98–110
Wang N, Er MJ, Han M (2014a) Parsimonious extreme learning machine using recursive orthogonal least squares. IEEE Trans Neural Netw Learn Syst 25(10):1828–1841
Wang N, Han M, Dong N, Er MJ (2014b) Constructive multi-output extreme learning machine with application to large tanker motion dynamics identification. Neurocomputing 128:59–72
Wang N, Sun JC, Er MJ, Liu YC (2015) A novel extreme learning control framework of unmanned surface vehicles. IEEE Trans Cybern. doi:10.1109/TCYB.2015.2423635
Wang N, Er MJ, Han M (2015b) Generalized single-hidden layer feedforward networks for regression problems. IEEE Trans Neural Netw Learn Syst 26(6):1161–1176
Wang Y, Li D, Du Y, Pan Z (2015) Anomaly detection in traffic using \(L_{1}\)-norm minimization extreme learning machine. Neurocomputing 149:415–425
Wolpert DH, Macready WG (1997) No free lunch theorems for optimization. IEEE Trans Evol Comput 1:67–82
**ao J, Zhou J, Li C, **ao H, Zhang W, Zhu W (2013) Multi-fault classification based on the two-stage evolutionary extreme learning machine and improved artificial bee colony algorithm. J Mech Eng Sci. doi:10.1177/0954406213496968
**n J, Wang Z, Qu L, Wang G (2013) Elastic extreme learning machine for big data classification. Neurocomputing 149:464–471
Xu Y, Shu Y (2006) Evolutionary extreme learning machine—based on particle swarm optimization. In: Advances in Neural Networks, Lecture Notes in Computer Science, vol. 3971, pp 644–652
Xue X, Yao M, Wu Z, Yang J (2014) Genetic ensemble of extreme learning machine. Neurocomputing 129:175–184
Yang XS (2008) Nature-inspired metaheuristic algorithms. Luniver Press, Beckington
Yang XS, Cui ZH, **ao RB, Gandomi AH, Karamanoglu M (2013) Swarm intelligence and bio-inspired computation: theory and applications. Elsevier, London
Yang H, Yi J, Zhao J, Dong Z (2013) Extreme learning machine based genetic algorithm and its application in power system economic dispatch. Neurocomputing 102:154–162
Yu J, Wang S, ** L (2008) Evolving artificial neural networks using an improved PSO and DPSO. Neurocomputing 71(4–6):1054–1060
Yu W, Zhuang F, He Q, Shi Z (2015) Learning deep representations via extreme learning machines. Neurocomputing 149:308–315
Zhao GP, Hen ZQ, Miao CY, Man ZH (2009) On improving the conditioning of extreme learning machine: a linear case. In: 7th International conference on information, communications and signal processing, 2009 (ICICS2009), Maucu, China, December 8th–10th, pp 1–5
Zhu QY, Qin AK, Suganthan PN, Huang GB (2005) Evolutionary extreme learning machine. Pattern Recogn 38:1759–1763
Author information
Authors and Affiliations
Corresponding author
Appendix: Interactions of the devised controller and BICs
Appendix: Interactions of the devised controller and BICs
In this section, the detailed information regarding the performance of the devised controller and its impact on the performance of BICs is given. In Tables 12, 13 and 14, some parameters are given which should be defined for clarifications:
-
Activation of the first strategy: This column indicates how many times the ill-conditioned ELMs are detected and discarded from the population.
-
Activation of the second strategy: This column indicates how many times the controller spurs the exploration/exploitation over the optimization procedure.
-
Activation of the third strategy: This column indicates how many times the controller selects the fitter ELM based on its generalization capability (Eq. (40)).
-
Performance and robustness improvement: The possible improvement in the performance and robustness of the self-controlled BICs in comparison to the basic BICs are listed in the last two columns.
Rights and permissions
About this article
Cite this article
Mozaffari, A., Azad, N.L. Self-controlled bio-inspired extreme learning machines for scalable regression and classification: a comprehensive analysis with some recommendations. Artif Intell Rev 46, 167–223 (2016). https://doi.org/10.1007/s10462-016-9461-2
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10462-016-9461-2