- 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. [West, Jeremy, Dan Ventura, and Sean Warnick. [http://cpms.byu.edu/springresearch/abstract-entry?id=861 Spring Research Presentation: A Theoretical Foundation for Inductive Transfer] (Abstract Only). Brigham Young University, College of Physical and Mathematical Sciences. 2007. Retrieved on2007 -08-05 .] 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 ontransfer of learning , although formal ties between the two fields are limited.Notably, scientists have developed algorithms for inductive transfer in
Markov logic network s [Mihalkova, Lilyana, Tuyen Huynh, and Raymond J. Mooney. [http://www.cs.utexas.edu/users/ml/papers/mihalkova-aaai07.pdf 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 on2007 -08-05 .] andBayesian networks . [Niculescu-Mizil, Alexandru, and Rich Caruana. [http://www.stat.umn.edu/~aistat/proceedings/data/papers/043.pdf 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 on2007 -08-05 .] Furthermore, researchers have applied techniques for transfer to problems in text classification, [Do, Cuong B. and Andrew Y. Ng. [http://books.nips.cc/papers/files/nips18/NIPS2005_0722.pdf Transfer learning for text classification.] Neural Information Processing Systems Foundation, NIPS*2005 Online Papers. Retrieved on2007 -08-05 .] [Raina, Rajat, Andrew Y. Ng, and Daphne Koller. [http://ai.stanford.edu/~ang/papers/icml06-transferinformativepriors.pdf Constructing Informative Priors using Transfer Learning] Proceedings of the Twenty-third International Conference on Machine Learning, 2006. Retrieved on2007 -08-05 .] spam filtering, [Bickel, Steffen. [http://www.ecmlpkdd2006.org/discovery_challenge2006_overview.pdf ECML-PKDD Discovery Challenge 2006 Overview] Proceedings of the ECML-PKDD Discovery Challenge Workshop, 2006. Retrieved on2007 -08-05 .] and urban combat simulation. [Gorski, Nicholas A., and John E. Laird. [http://www.eecs.umich.edu/~ngorski/papers/GorskiLaird_icmlTL-06.pdf Experiments in Transfer Across Multiple Learning Mechanisms] . Proceedings of the ICML-06 Workshop on Structural Knowledge Transfer for Machine Learning. Pittsburgh, PA. Retrieved on2007 -08-05 .] [Wenyuan Dai, Qiang Yang, Gui-Rong Xue and Yong Yu. [http://www.machinelearning.org/proceedings/icml2007/papers/72.pdf] 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] [Sinno Jialin Pan and Qiang Yang. [http://www.cse.ust.hk/~sinnopan/publications/TLsurvey_0822.pdf A Survey on Transfer Learning] . Latest version: Aug 22, 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. ]ee also
Multi-task learning References
Wikimedia Foundation. 2010.
