Abstract
Machine learning techniques are capable of talking, interpreting, creating, and even reasoning about virtually any subject. Also, their learning power has grown exponentially throughout the last years due to advances in hardware architecture. Nevertheless, most of these models still struggle regarding their practical usage since they require a proper selection of hyper-parameters, which are often empirically chosen. Such requirements are strengthened when concerning deep learning models, which commonly require a higher number of hyper-parameters. A collection of nature-inspired optimization techniques, known as meta-heuristics, arise as straightforward solutions to tackle such problems since they do not employ derivatives, thus alleviating their computational burden. Therefore, this work proposes a comparison among several meta-heuristic optimization techniques in the context of Deep Belief Networks hyper-parameter fine-tuning. An experimental setup was conducted over three public datasets in the task of binary image reconstruction and demonstrated consistent results, posing meta-heuristic techniques as a suitable alternative to the problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Usually, contrastive divergence with a single iteration is called CD-1.
- 2.
- 3.
- 4.
- 5.
Note that these values were empirically chosen according to their author’s definition.
References
Carreira-Perpiñán, M.A., Hinton, G.E.: On contrastive divergence learning. In: Cowell, R.G., Ghahramani, Z. (eds.) Proceedings of the Tenth International Workshop on Artificial Intelligence and Statistics. Society for Artificial Intelligence and Statistics, pp. 33–40 (2005)
Civicioglu, P.: Backtracking search optimization algorithm for numerical optimization problems. Appl. Math. Comput. 219(15), 8121–8144 (2013)
Hinton, G.E.: Training products of experts by minimizing contrastive divergence. Neural Comput. 14(8), 1771–1800 (2002)
Hinton, G.E.: A practical guide to training restricted Boltzmann machines. In: Montavon, G., Orr, G., Müller, K.R. (eds.) Neural Networks: Tricks of the Trade. Lecture Notes in Computer Science, vol. 7700, pp. 599–619. Springer, Berlin (2012)
Hinton, G.E., Osindero, S., Teh, Y.W.: A fast learning algorithm for deep belief nets. Neural Comput. 18(7), 1527–1554 (2006)
Kennedy, J., Eberhart, R.C.: Swarm Intelligence. Morgan Kaufmann Publishers Inc., San Francisco (2001)
Kuremoto, T., Kimura, S., Kobayashi, K., Obayashi, M.: Time series forecasting using restricted Boltzmann machine. In: International Conference on Intelligent Computing, pp. 17–22. Springer, Berlin (2012)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Levy, E., David, O.E., Netanyahu, N.S.: Genetic algorithms and deep learning for automatic painter classification. In: Proceedings of the 2014 Annual Conference on Genetic and Evolutionary Computation, pp. 1143–1150. ACM, New York (2014)
Liu, K., Zhang, L.M., Sun, Y.W.: Deep Boltzmann machines aided design based on genetic algorithms. In: Applied Mechanics and Materials, vol. 568, pp. 848–851. Trans Tech, Clausthal (2014)
Mahdavi, M., Fesanghary, M., Damangir, E.: An improved harmony search algorithm for solving optimization problems. Appl. Math. Comput. 188(2), 1567–1579 (2007)
Nickabadi, A., Ebadzadeh, M.M., Safabakhsh, R.: A novel particle swarm optimization algorithm with adaptive inertia weight. Appl. Soft Comput. 11, 3658–3670 (2011)
Passos, L.A., Papa, J.P.: Fine-tuning infinity restricted Boltzmann machines. In: 2017 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), pp. 63–70. IEEE, New York (2017)
Passos, L.A., Papa, J.P.: On the training algorithms for restricted Boltzmann machine-based models. Ph.D. thesis, Universidade Federal de São Carlos (2018)
Passos, L.A., Papa, J.P.: A metaheuristic-driven approach to fine-tune deep Boltzmann machines. Appl. Soft Comput., 105717 (2019, in press). https://www.sciencedirect.com/science/article/abs/pii/S1568494619304983
Passos, L.A., Rodrigues, D.R., Papa, J.P.: Fine tuning deep Boltzmann machines through meta-heuristic approaches. In: 2018 IEEE 12th International Symposium on Applied Computational Intelligence and Informatics (SACI), pp. 000,419–000,424. IEEE, New York (2018)
Passos, L.A., Rodrigues, D., Papa, J.P.: Quaternion-based backtracking search optimization algorithm. In: 2019 IEEE Congress on Evolutionary Computation. IEEE, New York (2019)
Passos, L.A., de Souza Jr, L.A., Mendel, R., Ebigbo, A., Probst, A., Messmann, H., Palm, C., Papa, J.P.: Barrett’s esophagus analysis using infinity restricted Boltzmann machines. J. Vis. Commun. Image Represent. 59, 475–485 (2019)
Pereira, C.R., Passos, L.A., Rodrigues, D., Nunes, S.A., Papa, J.P.: JADE-based feature selection for non-technical losses detection. In: VII ECCOMAS Thematic Conference on Computational Vision and Medical Image Processing: VipIMAGE 2019 (2019)
Rodrigues, D., Pereira, L.A.M., Almeida, T.N.S., Papa, J.P., Souza, A.N., Ramos, C.O., Yang, X.S.: BCS: a binary cuckoo search algorithm for feature selection. In: IEEE International Symposium on Circuits and Systems, pp. 465–468 (2013)
Rodrigues, D., de Rosa, G.H., Passos, L.A., Papa, J.P.: Adaptive improved flower pollination algorithm for global optimization. In: Nature-Inspired Computation in Data Mining and Machine Learning, pp. 1–21. Springer, Berlin (2020)
Rosa, G., Papa, J.P., Costa, K., Passos, L.A., Pereira, C., Yang, X.S.: Learning parameters in deep belief networks through firefly algorithm. In: IAPR Workshop on Artificial Neural Networks in Pattern Recognition, pp. 138–149. Springer, Berlin (2016)
Salakhutdinov, R., Hinton, G.: Deep Boltzmann machines. In: Artificial Intelligence and Statistics, pp. 448–455 (2009)
Smolensky, P.: Parallel distributed processing: explorations in the microstructure of cognition. In: Chap. Information Processing in Dynamical Systems: Foundations of Harmony Theory, pp. 194–281. MIT Press, Cambridge (1986)
Storn, R., Price, K.: Differential evolution–a simple and efficient heuristic for global optimization over continuous spaces. J. Glob. Optim. 11(4), 341–359 (1997)
Thornton, C., Hutter, F., Hoos, H.H., Leyton-Brown, K.: Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms. In: Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 847–855. ACM, New York (2013)
Tieleman, T.: Training restricted Boltzmann machines using approximations to the likelihood gradient. In: Proceedings of the 25th International Conference on Machine Learning (ICML ’08), pp. 1064–1071. ACM, New York (2008)
Wang, Y., Li, H.X., Huang, T., Li, L.: Differential evolution based on covariance matrix learning and bimodal distribution parameter setting. Appl. Soft Comput. 18, 232–247 (2014)
Whitley, D.: A genetic algorithm tutorial. Stat. Comput. 4(2), 65–85 (1994)
Wilcoxon, F.: Individual comparisons by ranking methods. Biom. Bull. 1(6), 80–83 (1945)
Yang, X.S.: Firefly algorithm, stochastic test functions and design optimisation. Int. J. Bio-Inspired Comput. 2(2), 78–84 (2010)
Yang, X.S., Deb, S.: Cuckoo search via lévy flights. In: Nature and Biologically Inspired Computing (NaBIC 2009). World Congress on, pp. 210–214. IEEE, New York (2009)
Yang, X.S., Deb, S.: Engineering optimisation by cuckoo search. Int. J. Math. Model. Numer. Optim. 1, 330–343 (2010)
Yang, X.S., Gandomi, A.H.: Bat algorithm: a novel approach for global engineering optimization. Eng. Comput. 29(5), 464–483 (2012)
Yang, S.S., Karamanoglu, M., He, X.: Flower pollination algorithm: a novel approach for multiobjective optimization. Eng. Optim. 46(9), 1222–1237 (2014)
Yosinski, J., Lipson, H.: Visually debugging restricted Boltzmann machine training with a 3D example. In: Representation Learning Workshop, 29th International Conference on Machine Learning (2012)
Zhang, J., Sanderson, A.C.: Jade: adaptive differential evolution with optional external archive. IEEE Trans. Evol. Comput. 13(5), 945–958 (2009)
Acknowledgements
This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior—Brasil (CAPES)—Finance Code 001. The authors also appreciate FAPESP grants #2013/07375-0, #2014/12236-1, #2016/19403-6, #2017/02286-0, #2017/25908-6, #2018/21934-5 and #2019/02205-5, and CNPq grants 307066/2017-7 and 427968/2018-6.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Passos, L.A., Rosa, G.H.d., Rodrigues, D., Roder, M., Papa, J.P. (2020). On the Assessment of Nature-Inspired Meta-Heuristic Optimization Techniques to Fine-Tune Deep Belief Networks. In: Iba, H., Noman, N. (eds) Deep Neural Evolution. Natural Computing Series. Springer, Singapore. https://doi.org/10.1007/978-981-15-3685-4_3
Download citation
DOI: https://doi.org/10.1007/978-981-15-3685-4_3
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-3684-7
Online ISBN: 978-981-15-3685-4
eBook Packages: Computer ScienceComputer Science (R0)