Abstract
Although high accuracies were achieved by artificial neural network (ANN), determining the optimal number of neurons in the hidden layer and the activation function is still an open issue. In this paper, the applicability of assigning the number of neurons in the hidden layer and the activation function randomly was investigated. Based on the findings, two novel versions of randomized ANNs, which are stochastic, and pruned stochastic, were proposed to achieve a higher accuracy without any time-consuming optimization stage. The proposed approaches were evaluated and validated by the basic versions of the popular randomized ANNs [1] are the random weight neural network [2], the random vector functional links [3] and the extreme learning machine [4] methods. In the stochastic version of randomized ANNs, not only the weights and biases of the neurons in the hidden layer but also the number of neurons in the hidden layer and each activation function were assigned randomly. In pruned stochastic version of these methods, the winner networks were pruned according to a novel strategy in order to produce a faster response. Proposed approaches were validated via 60 datasets (30 classification and 30 regression datasets). Obtained accuracies and time usages showed that both versions of randomized ANNs can be employed for classification and regression.
Similar content being viewed by others
References
Zhang L, Suganthan PN (2016) A survey of randomized algorithms for training neural networks. Inf Sci 364:146–155
Schmidt WF, Kraaijveld MA, Duin RPW (1992) Feed forward neural networks with random weights. In: IEEE, 11th international conference on pattern recognition, pp 1–4
Pao YH, Park GH, Sobajic DJ (1994) Learning and generalization characteristics of the random vector functional-link net. Neurocomputing 6(2):163–180
Huang G-B, Zhu Q, Siew CÃ (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501
Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4(2):251–257
Wang D (2016) Editorial?: Randomized algorithms for training neural networks. Inf Sci 364–365:126–128
Li M, Wang D (2017) Insights into randomized algorithms for neural networks: practical issues and common pitfalls. Inf Sci 382–383(December):170–178
Zhang L, Suganthan PN (2016) A comprehensive evaluation of random vector functional link networks. Inf Sci 367–368:1094–1105
Huang G, Bin Huang G, Song S, You K (2015) Trends in extreme learning machines: a review. Neural Netw 61:32–48
Bin Huang G (2015) What are extreme learning machines? filling the gap between Frank Rosenblatt’s dream and John von Neumann’s puzzle. Cogn Comput 7(3):263–278
Bin Huang G (2014) An insight into extreme learning machines: random neurons, random features and kernels. Cogn Comput 6(3):376–390
Hernández-Aguirre A, Koutsougeras C, Buckles BP (2002) Sample complexity for function learning tasks through linear neural networks. Lect Notes Comput Sci 2313:262–271
Porwal A, Carranza EJM, Hale M (2003) Artificial neural networks for mineral-potential mapping: a case study from Aravalli Province, Western India. Nat Resour Res 12(3):155–171
Das DP, Panda G (2004) Active mitigation of nonlinear noise processes using a novel filtered-s LMS algorithm. IEEE Trans Speech Audio Process 12(3):313–322
Dudek G (2016) Extreme learning machine as a function approximator: initialization of input weights and biases. Adv Intell Syst Comput 403:59–69
Ertuğrul ÖF (2016) Forecasting electricity load by a novel recurrent extreme learning machines approach. Int J Electr Power Energy Syst 78:429
Ertuğrul ÖF, Kaya Y (2016) Smart city planning by estimating energy efficiency of buildings by extreme learning machine. In: 4th international Istanbul smart grid congress and fair, ICSG 2016
Ertuğrul ÖF, Emin Tağluk M, Kaya Y, Tekin R (2013) EMG signal classification by extreme learning machine|EMG sinyallerinin agirigrenme makinesi ile siniflandirilmasi. In: 21st signal processing and communications applications conference SIU 2013
Li B, Li Y, Rong X (2013) The extreme learning machine learning algorithm with tunable activation function. Neural Comput Appl 22(3–4):531–539
Rychetsky M, Ortmann M, Glesner S (1998) Pruning and regularization techniques for feed forward nets applied on a real world data base. In: International symposium on neural computation, pp 603–609
Huang G-B, Chen L, Siew C-K (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. Trans Neural Netw 17(4):879–892
Huang G-B, Chen L (2008) Enhanced random search based incremental extreme learning machine. Neurocomputing 71(16–18):3460–3468
Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464–1480
Duin RPW, Juszczak P, Paclik P, Pekalska E, de Ridder D (2004) PR-Tools 4.0, a Matlab toolbox for pattern recognition, The Netherlands
Lichman M (2013) UCI machine learning repository [http://archive.ics.uci.edu/ml] Irvine, CA University of California, School of Information and Computer Sciences
Huang G, Zhu Q (2006) Extreme learning machine: a new learning scheme of feedforward neural networks. Neurocomputing 70:489–501
Ertuğrul ÖF, Altun Ş (2016) Developing correlations by extreme learning machine for calculating higher heating values of waste frying oils from their physical properties. Neural Comput Appl 28:3145
Zhu Q-Y, Qin AK, Suganthan PN, Huang G-B (2005) Evolutionary extreme learning machine. Pattern Recogn 38(10):1759–1763
Bin Huang G, Wang DH, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2(2):107–122
Feng G, Bin Huang G, Lin Q, Gay R (2009) Error minimized extreme learning machine with growth of hidden nodes and incremental learning. IEEE Trans Neural Netw 20(8):1352–1357
Cant E (2003) Pruning neural networks with distribution estimation algorithms. Neural Netw 25:790–800
Bin Huang G, Chen L (2007) Convex incremental extreme learning machine. Neurocomputing 70(16–18):3056–3062
Rong H-J, Ong Y-S, Tan A-H, Zhu Z (2008) A fast pruned-extreme learning machine for classification problem. Neurocomputing 72(1–3):359–366
Alpaydın E (2010) Introduction to machine learning, 2nd edn. The MIT Press, Cambridge, MA, London, England, pp 39, 79
Ratsch G, Onoda T, Muller KR (1998) An improvement of AdaBoost to avoid overfitting. In: Advances in neutral information processing systems, Kitakyushu, pp 506–509
Raymer ML, Doom TE, Kuhn LA, Punch WF (2003) Knowledge discovery in medical and biological datasets using a hybrid bayes classifier/evolutionary algorithm. IEEE Trans Syst Man Cybern 33:802–814
Ertuğrul ÖF, Tağluk ME (2016) A novel machine learning method based on generalized behavioral learning theory. Neural Comput Appl 28:3921
Demšar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1–30
Tang J, Deng C, Huang G-B (2015) Extreme learning machine for multilayer perceptron. IEEE Trans Neural Netw Learn Syst 27:1–13
Liang N-Y, Huang G-B, Saratchandran P, Sundararajan N (2006) A fast and accurate online sequential learning algorithm for feedforward networks. IEEE Trans Neural Netw 17(6):1411–1423
Cao J, Lin Z, Huang GB (2012) Self-adaptive evolutionary extreme learning machine. Neural Process Lett 36(3):285–305
Wang Y, Yuan Y, Yang X (2012) Bidirectional extreme learning machine for regression problem and its learning effectiveness. IEEE Trans Neural Netw Learn Syst 23(9):1498–1505
Alamo T, Tempo R, Luque A, Ramirez DR (2015) Randomized methods for design of uncertain systems: sample complexity and sequential algorithms. Automatica 52:160–172
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Ertuğrul, Ö.F. Two Novel Versions of Randomized Feed Forward Artificial Neural Networks: Stochastic and Pruned Stochastic. Neural Process Lett 48, 481–516 (2018). https://doi.org/10.1007/s11063-017-9752-x
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11063-017-9752-x