Inductive transfer

Inductive transfer, or transfer learning, is a research problem in machine learning that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem.[1] For example, the abilities acquired while learning to walk presumably apply when one learns to run, and knowledge gained while learning to recognize cars could apply when recognizing trucks. This area of research bears some relation to the long history of psychological literature on transfer of learning, although formal ties between the two fields are limited.

The earliest cited work on transfer in machine learning is attributed to Lorien Pratt who formulated the discriminability-based transfer (DBT) algorithm in 1993.[2] In 1997, the journal Machine Learning published a special issue devoted to Inductive Transfer[3] and by 1998, the field had advanced to include multi-task learning,[4] along with a more formal analysis of its theoretical foundations.[5] Learning to Learn,[6] edited by Sebastian Thrun and Pratt, is a comprehensive overview of the state of the art of inductive transfer at the time of its publication.

Inductive transfer has also been applied in cognitive science, with the journal Connection Science publishing a special issue on Reuse of Neural Networks through Transfer in 1996.[7]

Notably, scientists have developed algorithms for inductive transfer in Markov logic networks[8] and Bayesian networks.[9] Furthermore, researchers have applied techniques for transfer to problems in text classification,[10][11] spam filtering,[12] and urban combat simulation.[13] [14] [15]

There still exists much potential in this field while the "transfer" hasn't yet led to significant improvement in learning. Also, an intuitive understanding could be that "transfer means a learner can directly learn from other correlated learners". However, in this way, such a methodology in transfer learning, whose direction is illustrated by,[16][17] is not a hot spot in the area yet.

See also

References

  1. ↑ West, Jeremy, Dan Ventura, and Sean Warnick. Spring Research Presentation: A Theoretical Foundation for Inductive Transfer (Abstract Only). Brigham Young University, College of Physical and Mathematical Sciences. 2007. Retrieved on 2007-08-05.
  2. ↑ Pratt, L. Y. . Advances in Neural Information Processing Systems 5, pp. 204-211, Morgan-Kaufmann, 1993.
  3. ↑ Pratt, L. Y. and Thrun, S. , Machine Learning, Special Issue on Inductive Transfer, Vol. 28, No 1., Kluwer, July 1997
  4. ↑ Curwana, R., Multitask Learning, pp. 95-134 in Learning To Learn, Pratt L.Y. and Thrun, S. (eds), Kluwer, 1998
  5. ↑ Baxter, J., Theoretical Models of Learning to Learn, pp. 71-95 in Learning To Learn, Pratt L.Y. and Thrun, S. (eds), Kluwer, 1998
  6. ↑ Learning To Learn, Pratt L.Y. and Thrun, S. (eds), Kluwer, 1998
  7. ↑ Pratt, L., Connection Science: Special Issue: Reuse of Neural Networks through Transfer Vol. 8, Issue 2, 1996
  8. ↑ Mihalkova, Lilyana, Tuyen Huynh, and Raymond J. Mooney. Mapping and Revising Markov Logic Networks for Transfer Learning. Proceedings of the 22nd AAAI Conference on Artificial Intelligence (AAAI-2007), Vancouver, BC, pp. 608-614, July 2007. Retrieved on 2007-08-05.
  9. ↑ Niculescu-Mizil, Alexandru, and Rich Caruana. Inductive Transfer for Bayesian Network Structure Learning. Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics (AISTATS 2007), March 21–24, 2007. Retrieved on 2007-08-05.
  10. ↑ Do, Cuong B. and Andrew Y. Ng. Transfer learning for text classification. Neural Information Processing Systems Foundation, NIPS*2005 Online Papers. Retrieved on 2007-08-05.
  11. ↑ Raina, Rajat, Andrew Y. Ng, and Daphne Koller. Constructing Informative Priors using Transfer Learning Proceedings of the Twenty-third International Conference on Machine Learning, 2006. Retrieved on 2007-08-05.
  12. ↑ Bickel, Steffen. ECML-PKDD Discovery Challenge 2006 Overview Proceedings of the ECML-PKDD Discovery Challenge Workshop, 2006. Retrieved on 2007-08-05.
  13. ↑ Gorski, Nicholas A., and John E. Laird. Experiments in Transfer Across Multiple Learning Mechanisms. Proceedings of the ICML-06 Workshop on Structural Knowledge Transfer for Machine Learning. Pittsburgh, PA. Retrieved on 2007-08-05.
  14. ↑ Wenyuan Dai, Qiang Yang, Gui-Rong Xue and Yong Yu. Boosting for Transfer Learning. In Proceedings of The 24th Annual International Conference on Machine Learning (ICML'07) Corvallis, Oregon, USA, June 20–24, 2007. 193 - 200
  15. ↑ Sinno Jialin Pan and Qiang Yang. A Survey on Transfer Learning. Latest version: Nov 10, 2008. This is an online publication. It surveys the field of transfer learning (current version mainly focuses on transfer learning in classification, regression, clustering, dimensionality reduction and relational learning) and will be updated regularly.
  16. ↑ Lixin Duan, Ivor W. Tsang, Dong Xu and Tat-Seng Chua.Domain Adaptation from Multiple Sources via Auxiliary Classifiers Proceedings of the 26th International Conference of Machine Learning (ICML'09), Montreal Canada.
  17. ↑ Lei Jiang, Jian Zhang and Gabrielle Allen. Transferred Correlation Learning: An Incremental Approach for Neural Network Ensembles Proceedings of the 2010 International Joint Conference of Neural Networks (IJCNN'10), Barcelona, Spain.
This article is issued from Wikipedia - version of the Monday, April 25, 2016. The text is available under the Creative Commons Attribution/Share Alike but additional terms may apply for the media files.