Abstract
With Sobolev Training, neural networks are trained to fit target output values as well as target derivatives with respect to the inputs. This leads to better generalization and fewer required training examples for certain problems. In this paper, we present a training pipeline that enables Sobolev Training for regression problems where target derivatives are not directly available. Thus, we propose to use a least-squares estimate of the target derivatives based on function values of neighboring training samples. We show for a variety of black-box function regression tasks that our training pipeline achieves smaller test errors compared to the traditional training method. Since our method has no additional requirements on the data collection process, it has great potential to improve the results for various regression tasks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Czarnecki, W.M., Osindero, S., Jaderberg, M., Swirszcz, G., Pascanu, R.: Sobolev training for neural networks. In: Advances in Neural Information Processing Systems, pp. 4278–4287 (2017)
Drucker, H., Le Cun, Y.: Double backpropagation increasing generalization performance. In: IJCNN-91-Seattle International Joint Conference on Neural Networks, vol. 2, pp. 145–150. IEEE (1991)
Dua, D., Graff, C.: UCI machine learning repository (2017). http://archive.ics.uci.edu/ml
Gerritsma, J., Onnink, R., Versluis, A.: Geometry, resistance and stability of the Delft systematic Yacht hull series. Int. Shipbuild. Prog. 28(328), 276–297 (1981)
Hornik, K., Stinchcombe, M., White, H.: Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks. Neural Netw. 3(5), 551–560 (1990)
Kaya, H., Tüfekci, P., Gürgen, F.S.: Local and global learning methods for predicting power of a combined gas & steam turbine. In: Proceedings of the International Conference on Emerging Trends in Computer and Electronics Engineering ICETCEE, pp. 13–18 (2012)
Kingma, D., Ba, J.: Adam: A method for stochastic optimization. In: International Conference on Learning Representations (2014)
Lampinen, J., Selonen, A.: Multilayer perceptron training with inaccurate derivative information. In: Proceedings of 1995 IEEE International Conference on Neural Networks ICNN, vol. 95, pp. 2811–2815 (1995). Citeseer
Lee, J.W., Oh, J.H.: Hybrid learning of mapping and its Jacobian in multilayer neural networks. Neural Comput. 9(5), 937–958 (1997)
Masuoka, R., Thrun, S., Mitchell, T.M.: Constraining neural networks to fit target slopes (1993)
Mitchell, T.M., Thrun, S.B.: Explanation-based neural network learning for robot control. In: Advances in Neural Information Processing Systems, pp. 287–294 (1993)
Nocedal, J., Wright, S.J.: Numerical Optimization, 2nd edn. Springer, New York (2006). https://doi.org/10.1007/978-0-387-40065-5
Ortigosa, I., Lopez, R., Garcia, J.: A neural networks approach to residuary resistance of sailing Yachts prediction. In: Proceedings of the International Conference on Marine Engineering MARINE, vol. 2007, p. 250 (2007)
Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011)
Pukrittayakamee, A., et al.: Simultaneous fitting of a potential-energy surface and its corresponding force fields using feedforward neural networks. J. Chem. Phys. 130(13), 134101 (2009)
Pukrittayakamee, A., Hagan, M., Raff, L., Bukkapatnam, S.T., Komanduri, R.: Practical training framework for fitting a function and its derivatives. IEEE Trans. Neural Networks 22(6), 936–947 (2011)
Rifai, S., et al.: Higher order contractive auto-encoder. In: Gunopulos, D., Hofmann, T., Malerba, D., Vazirgiannis, M. (eds.) ECML PKDD 2011. LNCS (LNAI), vol. 6912, pp. 645–660. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-23783-6_41
Simard, P., Victorri, B., LeCun, Y., Denker, J.: Tangent prop-a formalism for specifying selected invariances in an adaptive network. In: Advances in Neural Information Processing Systems, pp. 895–903 (1992)
Surjanovic, S., Bingham, D.: Virtual library of simulation experiments: test functions and datasets (2013). http://www.sfu.ca/ssurjano. Accessed 7 Jan 2019
Tüfekci, P.: Prediction of full load electrical power output of a base load operated combined cycle power plant using machine learning methods. Int. J. Electr. Power Energy Syst. 60, 126–140 (2014)
U.S. Department of Commerce: Bureau of the Census, Census Of Population And Housing 1990 United States: Summary tape file 1a & 3a (computer files)
U.S. Department Of Commerce: Bureau Of The Census Producer, Washington, DC and Inter-university Consortium for Political and Social Research Ann Arbor, Michigan (1992)
U.S. Department of Justice: Bureau of Justice Statistics, Law Enforcement Management And Administrative Statistics, U.S. Department Of Commerce, Bureau Of The Census Producer, Washington, DC and Inter-university Consortium for Political and Social Research Ann Arbor, Michigan (computer file) (1992)
U.S. Department of Justice: Federal Bureau of Investigation, Crime in the united states (computer file) (1995)
Varga, D., Csiszárik, A., Zombori, Z.: Gradient regularization improves accuracy of discriminative models (2017)
Witkoskie, J.B., Doren, D.J.: Neural network models of potential energy surfaces: prototypical examples. J. Chem. Theory Comput. 1(1), 14–23 (2005)
Yeh, I.C.: Modeling of strength of high-performance concrete using artificial neural networks. Cem. Concr. Res. 28(12), 1797–1808 (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Kissel, M., Diepold, K. (2020). Sobolev Training with Approximated Derivatives for Black-Box Function Regression with Neural Networks. In: Brefeld, U., Fromont, E., Hotho, A., Knobbe, A., Maathuis, M., Robardet, C. (eds) Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2019. Lecture Notes in Computer Science(), vol 11907. Springer, Cham. https://doi.org/10.1007/978-3-030-46147-8_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-46147-8_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-46146-1
Online ISBN: 978-3-030-46147-8
eBook Packages: Computer ScienceComputer Science (R0)