Abstract
Transfer learning is a process to transfer knowledge learned in one or more source tasks to a related but more complex, unseen target task, in an effort to facilitate learning in the target task. Genetic programming (GP) is an evolutionary approach to generating computer programs for solving a given problem automatically. Transfer learning in GP has been investigated in complex Boolean and symbolic regression problems, but not much in image classification. In this paper, we propose a novel approach to use transfer learning in GP for image classification problems. Specifically, the proposed novel approach extends an existing state-of-the-art GP method by incorporating the ability to extract useful knowledge from simpler problems of a domain and reuse the extracted knowledge to solve complex problems of the domain. The proposed system has been compared with the baseline system (i.e., GP without using transfer learning) on multi-class texture classification problems from three widely-used texture datasets with different rotations and different levels of noise. The experimental results showed that the ability to reuse the extracted knowledge in the proposed GP method helps achieve better classification accuracy than the baseline GP method.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
Since GP-criptor is the state-of-the-art method and better than existing methods, we will not compare with other existing methods. This is not the main goal either.
References
Al-Sahaf, H., Zhang, M., Johnston, M., Verma, B.: Image descriptor: a genetic programming approach to multiclass texture classification. In: Proceedings of 2015 IEEE Congress on Evolutionary Computation, pp. 2460–2467. IEEE (2015)
Brodatz, P.: Textures: A Photographic Album for Artists and Designers. Dover Publications, New York (1999)
Chen, Q., Xue, B., Zhang, M.: Generalisation and domain adaptation in GP with gradient descent for symbolic regression. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 1137–1144 (2015)
Dinh, T.T.H., Chu, T.H., Nguyen, Q.U.: Transfer learning in genetic programming. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 1145–1151 (2015)
Gandomi, A.H., Alavi, A.H., Ryan, C.: Handbook of Genetic Programming Applications. Springer, Heidelberg (2015)
Gustafson, S.M., Hsu, W.H.: Layered learning in genetic programming for a cooperative Robot Soccer problem. In: Proceedings of the European Conference on Genetic Programming, pp. 291–301 (2001)
Gutstein, S., Fuentes, O., Freudenthal, E.: Knowledge transfer in deep convolutional neural nets. Int. J. Artif. Intell. Tools 17(3), 555–567 (2008)
Hien, N.T., Hoai, N.X., McKay, B.: A study on genetic programming with layered learning and incremental sampling. In: Proceedings of the IEEE Congress on Evolutionary Computation, pp. 1179–1185 (2011)
Hoang, T.H., McKay, R.I.B., Essam, D., Hoai, N.X.: On synergistic interactions between evolution, development and layered learning. IEEE Trans. Evol. Comput. 15(3), 287–312 (2011)
Iqbal, M., Browne, W.N., Zhang, M.: Reusing building blocks of extracted knowledge to solve complex, large-scale boolean problems. IEEE Trans. Evol. Comput. 18(4), 465–480 (2014)
Jackson, D., Gibbons, A.P.: Layered learning in boolean GP problems. In: Proceedings of the European Conference on Genetic Programming, pp. 148–159 (2007)
Jaśkowski, W., Krawiec, K., Wieloch, B.: Cross-task code reuse in genetic programming applied to visual learning. Int. J. Appl. Math. Comput. Sci. 24(1), 183–197 (2014)
Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. The MIT Press, Cambridge (1992)
Kylberg, G.: The Kylberg texture dataset v. 1.0. External report (Blue series) 35, Centre for Image Analysis, Swedish University of Agricultural Sciences and Uppsala University, Uppsala, Sweden (2011)
Niculescu-Mizil, A., Caruana, R.: Inductive transfer for Bayesian network structure learning. J. Mach. Learn. Res. 27, 167–181 (2012)
Ojala, T., Mäenpää, T., Pietikäinen, M., Viertola, J., Kyllonen, J., Huovinen, S.: Outex - new framework for empirical evaluation of texture analysis algorithms. In: Proceedings of the International Conference on Pattern Recognition, pp. 701–706 (2002)
Pan, S.J., Yang, Q.: A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345–1359 (2010)
Perez, C.B., Olague, G.: Evolutionary learning of local descriptor operators for object recognition. In: Proceedings of the 11th Annual Conference on Genetic and Evolutionary Computation, pp. 1051–1058. ACM (2009)
Song, A., Loveard, T., Ciesielski, V.: Towards genetic programming for texture classification. In: Proceedings of the Australian Joint Conference on Artificial Intelligence, pp. 461–472 (2001)
Stone, P., Veloso, M.: Layered learning. In: Proceedings of the European Conference on Machine Learning, pp. 369–381 (2000)
Torrey, L., Shavlik, J.: Transfer learning. In: Handbook of Research on Machine Learning Applications and Trends: Algorithms, Methods, and Techniques, chap. 11, pp. 242–264. IGI Global (2010)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Iqbal, M., Xue, B., Zhang, M. (2016). Reusing Extracted Knowledge in Genetic Programming to Solve Complex Texture Image Classification Problems. In: Bailey, J., Khan, L., Washio, T., Dobbie, G., Huang, J., Wang, R. (eds) Advances in Knowledge Discovery and Data Mining. PAKDD 2016. Lecture Notes in Computer Science(), vol 9652. Springer, Cham. https://doi.org/10.1007/978-3-319-31750-2_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-31750-2_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-31749-6
Online ISBN: 978-3-319-31750-2
eBook Packages: Computer ScienceComputer Science (R0)