Abstract
Deep neural networks proved to be a very useful and powerful tool with many applications. In order to achieve good learning results, the network architecture has, however, to be carefully designed, which requires a lot of experience and knowledge. Using an evolutionary process to develop new network topologies can facilitate this process. The limiting factor is the speed of evaluation of a single specimen (a single network architecture), which includes learning based on a large dataset. In this paper we propose a new approach which uses subsets of the original training set to approximate the fitness. We describe a co-evolutionary algorithm and discuss its key elements. Finally we draw conclusions from experiments and outline plans for future work.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst. 25(NIPS2012), 1–9 (2012)
Bengio, Y., Ducharme, R., Vincent, P., Janvin, C.: A neural probabilistic language model. J. Mach. Learn. Res. 3, 1137–1155 (2003)
Ng, A.Y.: Feature selection, L1 vs. L2 regularization, and rotational invariance. In: Twenty-First International Conference on Machine Learning - ICML 2004, p. 78 (2004)
Srivastava, N., Hinton, G.E., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. (JMLR) 15, 1929–1958 (2014)
Courville, A., Bengio, Y., Vincent, P.: Why does unsupervised pre-training help deep learning? J. Mach. Learn. Res. 9(2007), 201–208 (2010)
Koza, J.R.: Human-competitive results produced by genetic programming. Genet. Prog. Evolvable Mach. 11(3–4), 251–284 (2010)
Schmidt, M.D., Lipson, H.: Coevolution of fitness predictors. IEEE Trans. Evol. Comput. 12(6), 736–749 (2008)
Funika, W., Koperek, P.: Genetic programming in automatic discovery of relationships in computer system monitoring data. In: Wyrzykowski, R., Dongarra, J., Karczewski, K., Waśniewski, J. (eds.) PPAM 2013. LNCS, vol. 8384, pp. 371–380. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-642-55224-3_35
LeCun, Y., Cortes, C.: MNIST handwritten digit database (2010)
McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bull. Math. Biophys. 5(4), 115–133 (1943)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2323 (1998)
Montana, D.J., Davis, L.: Training feedforward neural networks using genetic algorithms. In: Proceedings of the 11th International Joint Conference on Artificial Intelligence - Volume 1, vol. 89, pp. 762–767 (1989)
Siebel, N.T., Bötel, J., Sommer, G.: Efficient neural network pruning during neuro-evolution. In: Proceedings of the International Joint Conference on Neural Networks, pp. 2920–2927 (2009)
Stanley, K.O., D’Ambrosio, D.B., Gauci, J.: A hypercube-based encoding for evolving large-scale neural networks. Artif. Life 15(2), 185–212 (2009)
Fernando, C., Banarse, D., Reynolds, M., Besse, F., Pfau, D., Jaderberg, M., Lanctot, M., Wierstra, D.: Convolution by evolution: differentiable pattern producing networks. CoRR, abs/1606.02580 (2016)
David, O.E., Greental, I.: Genetic algorithms for evolving deep neural networks. In: GECCO Competition 2014, pp. 1451–1452 (2014)
Loshchilov, I., Hutter, F.: CMA-ES for hyperparameter optimization of deep neural networks. CoRR, abs/1604.07269 (2016)
Bongard, J.C., Lipson, H.: Nonlinear system identification using coevolution of models and tests. IEEE Trans. Evol. Comput. 9(4), 361–384 (2005)
Jin, Y.: A comprehensive survey of fitness approximation in evolutionary computation. Soft Comput. 9(1), 3–12 (2005)
Schmidt, M., Lipson, H.: Co-evolving fitness predictors for accelerating and reducing evaluations. GPTP 2006, 1 (2006)
Funika, W., Koperek, P.: Spatial-oriented neural network encoding for neuro-evolution. In: Proceeding of Cracow Grid Workshop (CGW 2016), pp. 37–38. ACC Cyfronet AGH, Krakow (2016)
Ciresan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Deep big simple neural nets excel on handwritten digit recognition. CoRR, abs/1003.0358 (2010)
Acknowledgement
The research is supported by AGH grant no. 11.11.230.337 and by the PL Grid project with computational resources to carry out experiments.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Funika, W., Koperek, P. (2018). Co-evolution of Fitness Predictors and Deep Neural Networks. In: Wyrzykowski, R., Dongarra, J., Deelman, E., Karczewski, K. (eds) Parallel Processing and Applied Mathematics. PPAM 2017. Lecture Notes in Computer Science(), vol 10777. Springer, Cham. https://doi.org/10.1007/978-3-319-78024-5_48
Download citation
DOI: https://doi.org/10.1007/978-3-319-78024-5_48
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-78023-8
Online ISBN: 978-3-319-78024-5
eBook Packages: Computer ScienceComputer Science (R0)