Abstract
Deep learning (DL) is one of the most emerging types of contemporary machine learning techniques that mimic the cognitive patterns of animal visual cortex to learn the new abstract features automatically by deep and hierarchical layers. DL is believed to be a suitable tool so far for extracting insights from very huge volume of so-called big data. Nevertheless, one of the three āVā or big data is velocity that implies the learning has to be incremental as data are accumulating up rapidly. DL must be fast and accurate. By the technical design of DL, it is extended from feed-forward artificial neural network with many multi-hidden layers of neurons called deep neural network (DNN). In the training process of DNN, it has certain inefficiency due to very long training time required. Obtaining the most accurate DNN within a reasonable run-time is a challenge, given there are potentially many parameters in the DNN model configuration and high dimensionality of the feature space in the training dataset. Meta-heuristic has a history of optimizing machine learning models successfully. How well meta-heuristic could be used to optimize DL in the context of big data analytics is a thematic topic which we pondered on in this paper. As a position paper, we review the recent advances of applying meta-heuristics on DL, discuss about their pros and cons and point out some feasible research directions for bridging the gaps between meta-heuristics and DL.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Hinton, G. E., Osindero, S., and Teh, Y. W. āA fast learning algorithm for deep belief netsā, Neural Computation. 2006;18(7):1527ā1554
Yu Kai, Jia Lei, Chen Yuqiang, and Xu Wei. āDeep learning: yesterday, today, and tomorrowā, Journal of Computer Research and Development. 2013;50(9):1799ā1804
ILSVRC2012. Large Scale Visual Recognition Challenge 2012 [Internet]. [Updated 2013-08-01]. Available from: http://www.imagenet. Org/challenges/LSVRC/2012/
Izadinia, Hamid, et al. āDeep classifiers from image tags in the wildā. In: Proceedings of the 2015 Workshop on Community-Organized Multimodal Mining: Opportunities for Novel Solutions; ACM; 2015
Gudise, V. G. and Venayagamoorthy, G. K. āComparison of particle swarm optimization and back propagation as training algorithms for neural networksā. In: Proceedings of In Swarm Intelligence Symposium SISā03; 2006. p. 110ā117
Marc Claesen, Bart De Moor, āHyperparameter Search in Machine Learningā, MIC 2015: The XI Metaheuristics International Conference, Agadir, June 7ā10, 2015, pp. 14-1 to 14-5
Steven R. Young, Derek C. Rose, Thomas P. Karnowski, Seung-Hwan Lim, Robert M. Patton, āOptimizing deep learning hyper-parameters through an evolutionary algorithmā, Proceedings of the Workshop on Machine Learning in High-Performance Computing Environments, ACM, 2015
Papa, Joao P.; Rosa, Gustavo H.; Marana, Aparecido N.; Scheirer, Walter; Cox, David D. āModel selection for Discriminative Restricted Boltzmann Machines through meta-heuristic techniquesā. Journal of Computational Science, v.9, SI, p. 14ā18, July 2015
Xin-She Yang, āEngineering Optimization: An Introduction with Metaheuristic Applicationsā, Wiley, ISBN: 978-0-470-58246-6, 347 pages, June 2010
Goldberg, D. E. and Holland, J. H. āGenetic algorithms and machine learningā. Machine Learning. 1988;3(2):95ā99
Iztok Fister Jr., Xin-She Yang, Iztok Fister, Janez Brest, Dusan Fister, āA Brief Review of Nature-Inspired Algorithms for Optimization ā, ELEKTROTEHNISKI VESTNIK, 80(3): 1ā7, 2013
Kennedy, J. āParticle Swarm Optimizationā; Springer, USA; 2010. p. 760ā766
Glover, F. āTabu search-part Iā. ORSA Journal on Computing. 1989;1(3):190ā206
Xin-She Yang, Suash Deb, Simon Fong, āMetaheuristic Algorithms: Optimal Balance of Intensification and Diversificationā, Applied Mathematics & Information Sciences, 8(3), May 2014, pp. 1ā7
C. Blum, and A. Roli, āMetaheuristics in combinatorial optimization: Overview and conceptual comparisonā, ACM Computing Surveys, Volume 35, Issue 3, 2003, pp. 268ā308
Simon Fong, Suash Deb, Xin-She Yang, āA heuristic optimization method inspired by wolf preying behaviorā, Neural Computing and Applications 26 (7), Springer, pp. 1725ā1738
Suash Deb, Simon Fong, Zhonghuan Tian, āElephant Search Algorithm for optimization problemsā, 2015 Tenth International Conference on Digital Information Management (ICDIM), IEEE, Jeju, 21ā23 Oct. 2015, pp. 249ā255
Beheshti, Z. and Shamsuddin, S. M. H. āA review of population-based meta-heuristic algorithmsā. International Journal of Advances in Soft Computing & Its Applications, 2013;5(1):1ā35
Simon Fong, Xi Wang, Qiwen Xu, Raymond Wong, Jinan Fiaidhi, Sabah Mohammed, āRecent advances in metaheuristic algorithms: Does the Makara dragon exist?ā, The Journal of Supercomputing, Springer, 24 December 2015, pp. 1ā23
Gudise, V. G. and Venayagamoorthy, G. K. āComparison of particle swarm optimization and back propagation as training algorithms for neural networksā. In: Proceedings of In Swarm Intelligence Symposium SISā03; 2006. p. 110ā117
Zhang, J. R., Zhang, J., Lok, T. M., and Lyu, M. R. āA hybrid particle swarm optimizationāback-propagation algorithm for feed forward neural network trainingā. Applied Mathematics and Computation. 2007;185(2):1026ā1037
Juang, C. F. āA hybrid of genetic algorithm and particle swarm optimization for recurrent network designā. Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions 2004;34(2):997ā1006
Meissner, M., Schmuker, M., and Schneider, G. āOptimized particle swarm optimization (OPSO) and its application to artificial neural network trainingā. BMC Bioinformatics. 2006;7(1):125
Leung, F. H., Lam, H. K., Ling, S. H., and Tam, P. K. āTuning of the structure and parameters of a neural network using an improved genetic algorithmā. IEEE Transactions on Neural Networks. 2003;14(1):79ā88
L.M. Rasdi Rere, Mohamad Ivan Fanany, Aniati Murni Arymurthy, āSimulated Annealing Algorithm for Deep Learningā, The Third Information Systems International Conference, Procedia Computer Science 72 (2015), pp. 137ā144
Hinton, G. E., āTraining products of experts by minimizing contrastive divergenceā, Neural Computing, 2002 Aug;14(8):1771ā800
Maass, W. āNetworks of spiking neurons: The third generation of neural network modelsā. Neural Networks. 1997;10(9):1659ā1671
Simon Fong, Ricardo Brito, Kyungeun Cho, Wei Song, Raymond Wong, Jinan Fiaidhi, Sabah Mohammed, āGPU-enabled back-propagation artificial neural network for digit recognition in parallelā, The Journal of Supercomputing, Springer, 10 February 2016, pp. 1ā19
Iztok Fister Jr., Simon Fong, Janez Brest, and Iztok Fister, āA Novel Hybrid Self-Adaptive Bat Algorithm,ā The Scientific World Journal, vol. 2014, Article ID 709738, 12 pages, 2014. doi:10.1155/2014/709738
Qun Song, Simon Fong, Rui Tang, āSelf-Adaptive Wolf Search Algorithmā, 5th International Congress on Advanced Applied Informatics, July 10ā14, 2016, Kumamoto City International Center, Kumamoto, Japan
Acknowledgements
The authors are thankful for the financial support from the Research Grant called āA Scalable Data Stream Mining Methodology: Stream-based Holistic Analytics and Reasoning in Parallel,ā Grant no. FDCT/126/2014/A3, offered by the University of Macau, FST, RDAO and the FDCT of Macau SAR government.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2018 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Fong, S., Deb, S., Yang, Xs. (2018). How Meta-heuristic Algorithms Contribute to Deep Learning in the Hype of Big Data Analytics. In: Sa, P., Sahoo, M., Murugappan, M., Wu, Y., Majhi, B. (eds) Progress in Intelligent Computing Techniques: Theory, Practice, and Applications. Advances in Intelligent Systems and Computing, vol 518. Springer, Singapore. https://doi.org/10.1007/978-981-10-3373-5_1
Download citation
DOI: https://doi.org/10.1007/978-981-10-3373-5_1
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-10-3372-8
Online ISBN: 978-981-10-3373-5
eBook Packages: EngineeringEngineering (R0)