Advertisement

Regularized Recurrent Neural Networks for Data Efficient Dual-Task Learning

  • Sigurd Spieckermann
  • Siegmund Düll
  • Steffen Udluft
  • Thomas Runkler
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8681)

Abstract

We introduce a regularization technique to improve system identification for dual-task learning with recurrent neural networks. In particular, the method is introduced using the Factored Tensor Recurrent Neural Networks first presented in [1]. Our goal is to identify a dynamical system with few available observations by augmenting them with data from a sufficiently observed similar system. In our previous work, we discovered that the model accuracy degrades whenever little data of the system of interest is available. The presented regularization term in this work allows to significantly reduce the model error thereby improving the exploitation of knowledge of the well observed system. This scenario is crucial in many real world applications, where data efficiency plays an important role. We motivate the problem setting and our regularized dual-task learning approach by industrial use cases, e.g. gas or wind turbine modeling for optimization and monitoring. Then, we formalize the problem and describe our regularization term by which the learning objective of the Factored Tensor Recurrent Neural Network is extended. Finally, we demonstrate its effectiveness on the cart-pole and mountain car benchmarks.

Keywords

multi-task learning recurrent neural networks factored tensor recurrent neural networks system identification dynamical systems regularization 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Spieckermann, S., Düll, S., Udluft, S., Hentschel, A., Runkler, T.: Exploiting similarity in system identification tasks with recurrent neural networks. In: European Symposium on Artificial Neural Networks, ESANN, pp. 473–478 (2014)Google Scholar
  2. 2.
    Schäfer, A.M., Udluft, S., Zimmermann, H.G.: The recurrent control neural network. In: European Symposium on Artificial Neural Networks, ESANN, pp. 319–324 (2007)Google Scholar
  3. 3.
    Bailer-Jones, C.A.L., MacKay, D.J.C., Withers, P.J.: A recurrent neural network for modelling dynamical systems. Network: Computation in Neural Systems 9(4), 531–547 (1998)CrossRefzbMATHGoogle Scholar
  4. 4.
    Schäfer, A.M., Schneegass, D., Sterzing, V., Udluft, S.: A neural reinforcement learning approach to gas turbine control. In: Proceedings of the International Joint Conference on Neural Networks, pp. 1691–1696 (August 2007)Google Scholar
  5. 5.
    Sutskever, I., Martens, J., Hinton, G.E.: Generating text with recurrent neural networks. In: Proceedings of the 28th International Conference on Machine Learning, pp. 1017–1024 (2011)Google Scholar
  6. 6.
    Taylor, G.W., Hinton, G.E.: Factored conditional restricted boltzmann machines for modeling motion style. In: Proceedings of the 26th International Conference on Machine Learning, pp. 1025–1032 (2009)Google Scholar
  7. 7.
    Florian, R.V.: Correct equations for the dynamics of the cart-pole system. Center for Cognitive and Neural Studies (Coneural), Romania (2007)Google Scholar
  8. 8.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, vol. 1. Cambridge University Press (1998)Google Scholar
  9. 9.
    Bergstra, J., Breuleux, O., Bastien, F., Lamblin, P., Pascanu, R., Desjardins, G., Turian, J., Warde-Farley, D., Bengio, Y.: Theano: a CPU and GPU math expression compiler. In: Proceedings of the Python for Scientific Computing Conference (SciPy). Oral Presentation (2010)Google Scholar
  10. 10.
    Martens, J., Sutskever, I.: Learning recurrent neural networks with Hessian-Free Optimization. In: Proceedings of the 28th International Conference on Machine Learning, pp. 1033–1040 (2011)Google Scholar
  11. 11.
    Martens, J., Sutskever, I.: Training deep and recurrent networks with Hessian-Free Optimization. In: Montavon, G., Orr, G.B., Müller, K.-R. (eds.) NN: Tricks of the Trade, 2nd edn. LNCS, vol. 7700, pp. 479–535. Springer, Heidelberg (2012)Google Scholar
  12. 12.
    Düll, S., Hans, A., Udluft, S.: The markov decision process extraction network. In: European Symposium on Artificial Neural Networks, ESANN (2010)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Sigurd Spieckermann
    • 1
    • 2
  • Siegmund Düll
    • 1
    • 3
  • Steffen Udluft
    • 1
  • Thomas Runkler
    • 1
    • 2
  1. 1.Siemens Corporate Technology, Learning SystemsMunichGermany
  2. 2.Department of InformaticsTechnical University of MunichGarchingGermany
  3. 3.Machine LearningBerlin University of TechnologyBerlinGermany

Personalised recommendations