Skip to main content
Springer Nature Link
Log in

Image Transformation: Inductive Transfer between Multiple Tasks Having Multiple Outputs

  • Conference paper
Advances in Artificial Intelligence (Canadian AI 2008)

Part of the book series: Lecture Notes in Computer Science ((LNAI,volume 5032))

Abstract

Previous research has investigated inductive transfer for single output modeling problems such as classification or prediction of a scalar. Little research has been done in the area of inductive transfer applied to tasks with multiple outputs. We report the results of using Multiple Task Learning (MTL) neural networks and Context-sensitive Multiple Task Learning (csMTL) on a domain of image transformation tasks. Models are developed to transform synthetic images of neutral (passport) faces to that of corresponding images of angry, happy and sad faces. The results are inconclusive for MTL, however they demonstrate that inductive transfer with csMTL is beneficial. When the secondary tasks have sufficient numbers of training examples from which to provide transfer, csMTL models are able to transform images more accurately than standard single task learning models.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Similar content being viewed by others

References

  1. Baxter, J.: Learning model bias. In: Touretzky, D.S., Mozer, M.C., Hasselmo, M.E. (eds.) Advances in Neural Information Processing Systems, vol. 8, pp. 169–175. MIT Press, Cambridge (1996)

    Google Scholar 

  2. Caruana, R.A.: Multitask learning: A knowledge-based source of inductive bias. In: Proceedings of the tenth international conference on machine learning, June 1993, pp. 41–48 (1993)

    Google Scholar 

  3. Caruana, R.A.: Multitask learning. Machine Learning 28, 41–75 (1997)

    Article  Google Scholar 

  4. Heskes, T.: Empirical bayes for learning to learn. In: Proceedings of the Int. Conference on Machine Learning (ICML 2000), pp. 367–374 (2000)

    Google Scholar 

  5. Jebara, T.: Multi-task feature and kernel selection for svms. In: Proceedings of the Int. Conference on Machine Learning (ICML 2004), pp. 185–192 (2004)

    Google Scholar 

  6. Micchelli, C.A., Pontil, M.: Kernels for multi-task learning. In: Proceedings of the 18th Conferences on Neural Information Processing Systems (NIPS 2005) (2005)

    Google Scholar 

  7. Mitchell, T.: Neural Networks for Face Recognition. Carnegie Mellon University (2007), http://www.cs.cmu.edu/~tom/faces.html

  8. O’Quinn, R., Silver, D.L., Poirier, R.: Continued practice and consolidation of a learning task. In: Proceedings of the Meta-Learning Workshop, 22nd Int. Conference on Machine Learning (ICML 2005), Bonn, Germany (2005)

    Google Scholar 

  9. Pratt, L.Y.: Discriminability-based transfer between neural networks. In: Giles, C.L., Hanson, S.J., Cowan, J.D. (eds.) Advances in Neural Information Processing Systems, vol. 5, pp. 204–211 (1993)

    Google Scholar 

  10. Silver, D.L., Mercer, R.E.: The parallel transfer of task knowledge using dynamic learning rates based on a measure of relatedness. In: Learning to Learn, pp. 213–233 (1997)

    Google Scholar 

  11. Silver, D.L., Mercer, R.E.: The task rehearsal method of life-long learning: Overcoming impoverished data. In: Advances in Artificial Intelligence, 15th Conference of the Canadian Society for Computational Studies of Intelligence (AI 2002), pp. 90–101 (2002)

    Google Scholar 

  12. Silver, D.L., Poirier, R.: Sequential consolidation of learned task knowledge. In: Webb, G.I., Yu, X. (eds.) AI 2004. LNCS (LNAI), vol. 3339, pp. 217–232. Springer, Heidelberg (2004)

    Google Scholar 

  13. Silver, D.L., Poirier, R.: Context-sensitive mtl networks for machine lifelong learning. In: Proceedings of the 20th Florida Artificial Intelligence Research Society Conference (FLAIRS 2007) (May 2007)

    Google Scholar 

  14. Thrun, S.: Lifelong learning algorithms. In: Learning to Learn, pp. 181–209. Kluwer Academic Publishers, Dordrecht (1997)

    Google Scholar 

  15. Utgoff, P.E.: Machine Learning of Inductive Bias. Kluwer Academc Publisher, Boston (1986)

    Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Jodrey School of Computer Science, Acadia University, Wolfville, NS, Canada, B4P 2R6

    Daniel L. Silver & Liangliang Tu

Authors
  1. Daniel L. Silver
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Liangliang Tu
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Sabine Bergler

Rights and permissions

Reprints and permissions

Copyright information

© 2008 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Silver, D.L., Tu, L. (2008). Image Transformation: Inductive Transfer between Multiple Tasks Having Multiple Outputs. In: Bergler, S. (eds) Advances in Artificial Intelligence. Canadian AI 2008. Lecture Notes in Computer Science(), vol 5032. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-68825-9_28

Download citation

  • DOI: https://doi.org/10.1007/978-3-540-68825-9_28

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-68821-1

  • Online ISBN: 978-3-540-68825-9

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics