Transfer learning

Source: Wikipedia, the free encyclopedia.
Illustration of transfer learning

Transfer learning (TL) is a technique in

image classification, knowledge gained while learning to recognize cars could be applied when trying to recognize trucks. This topic is related to the psychological literature on transfer of learning, although practical ties between the two fields are limited. Reusing/transferring information from previously learned tasks to new tasks has the potential to significantly improve learning efficiency.[2]

Since transfer learning makes use of training with multiple objective functions it is related to cost-sensitive machine learning and multi-objective optimization.[3]

History

In 1976, Bozinovski and Fulgosi published a paper addressing transfer learning in neural network training.[4][5] The paper gives a mathematical and geometrical model of the topic. In 1981, a report considered the application of transfer learning to a dataset of images representing letters of computer terminals, experimentally demonstrating positive and negative transfer learning.[6]

In 1992, Pratt formulated the discriminability-based transfer (DBT) algorithm.[7]

In 1997, Pratt and Thrun guest-edited a special issue of Machine Learning devoted to transfer learning,[8] and by 1998, the field had advanced to include multi-task learning,[9] along with more formal theoretical foundations.[10] Learning to Learn,[11] edited by Thrun and Pratt, is a 1998 review of the subject.

Transfer learning has been applied in cognitive science. Pratt guest-edited an issue of Connection Science on reuse of neural networks through transfer in 1996.[12]

Ng said in his NIPS 2016 tutorial[13][14][15] that TL would become the next driver of machine learning commercial success after supervised learning.

In the 2020 paper, "Rethinking Pre-Training and self-training",[16] Zoph et al. reported that pre-training can hurt accuracy, and advocate self-training instead.

Applications

Algorithms are available for transfer learning in

spam filtering.[26]

In 2020, it was discovered that, due to their similar physical natures, transfer learning is possible between

neural networks and convolutional neural networks were improved[28] through transfer learning both prior to any learning (compared to standard random weight distribution) and at the end of the learning process (asymptote). That is, results are improved by exposure to another domain. Moreover, the end-user of a pre-trained model can change the structure of fully-connected layers to improve performance.[29]

Software

Transfer learning and domain adaptation

Several compilations of transfer learning and domain adaptation algorithms have been implemented:

  • ADAPT[30] (Python)
  • TLlib[31] (Python)
  • Domain-Adaptation-Toolbox[32] (Matlab)

See also

References

  1. ^ West, Jeremy; Ventura, Dan; Warnick, Sean (2007). "Spring Research Presentation: A Theoretical Foundation for Inductive Transfer". Brigham Young University, College of Physical and Mathematical Sciences. Archived from the original on 2007-08-01. Retrieved 2007-08-05.
  2. S2CID 53774629
    .
  3. ^ Cost-Sensitive Machine Learning. (2011). USA: CRC Press, Page 63, https://books.google.de/books?id=8TrNBQAAQBAJ&pg=PA63
  4. ^ Stevo. Bozinovski and Ante Fulgosi (1976). "The influence of pattern similarity and transfer learning upon the training of a base perceptron B2." (original in Croatian) Proceedings of Symposium Informatica 3-121-5, Bled.
  5. ^ Stevo Bozinovski (2020) "Reminder of the first paper on transfer learning in neural networks, 1976". Informatica 44: 291–302.
  6. ^ S. Bozinovski (1981). "Teaching space: A representation concept for adaptive pattern classification." COINS Technical Report, the University of Massachusetts at Amherst, No 81-28 [available online: UM-CS-1981-028.pdf]
  7. ^ Pratt, L. Y. (1992). "Discriminability-based transfer between neural networks" (PDF). NIPS Conference: Advances in Neural Information Processing Systems 5. Morgan Kaufmann Publishers. pp. 204–211.
  8. ^ Pratt, L. Y.; Thrun, Sebastian (July 1997). "Machine Learning - Special Issue on Inductive Transfer". link.springer.com. Springer. Retrieved 2017-08-10.
  9. ^ Caruana, R., "Multitask Learning", pp. 95-134 in Thrun & Pratt 2012
  10. ^ Baxter, J., "Theoretical Models of Learning to Learn", pp. 71-95 Thrun & Pratt 2012
  11. ^ Thrun & Pratt 2012.
  12. ^ Pratt, L. (1996). "Special Issue: Reuse of Neural Networks through Transfer". Connection Science. 8 (2). Retrieved 2017-08-10.
  13. ^ NIPS 2016 tutorial: "Nuts and bolts of building AI applications using Deep Learning" by Andrew Ng, archived from the original on 2021-12-19, retrieved 2019-12-28
  14. ^ "NIPS 2016 Schedule". nips.cc. Retrieved 2019-12-28.
  15. ^ Nuts and bolts of building AI applications using Deep Learning, slides
  16. arXiv:2006.06882
    . Retrieved 2022-12-20.
  17. ^ Mihalkova, Lilyana; Huynh, Tuyen; Mooney, Raymond J. (July 2007), "Mapping and Revising Markov Logic Networks for Transfer" (PDF), Learning Proceedings of the 22nd AAAI Conference on Artificial Intelligence (AAAI-2007), Vancouver, BC, pp. 608–614, retrieved 2007-08-05{{citation}}: CS1 maint: location missing publisher (link)
  18. ^ Niculescu-Mizil, Alexandru; Caruana, Rich (March 21–24, 2007), "Inductive Transfer for Bayesian Network Structure Learning" (PDF), Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics (AISTATS 2007), retrieved 2007-08-05
  19. arXiv:1810.09433
  20. ISBN 978-1-4503-5544-5
    .
  21. S2CID 54066723
    .
  22. ^ Banerjee, Bikramjit, and Peter Stone. "General Game Learning Using Knowledge Transfer." IJCAI. 2007.
  23. ^ Do, Chuong B.; Ng, Andrew Y. (2005). "Transfer learning for text classification". Neural Information Processing Systems Foundation, NIPS*2005 (PDF). Retrieved 2007-08-05.
  24. ^ Rajat, Raina; Ng, Andrew Y.; Koller, Daphne (2006). "Constructing Informative Priors using Transfer Learning". Twenty-third International Conference on Machine Learning (PDF). Retrieved 2007-08-05.
  25. S2CID 25739012
    .
  26. ^ Bickel, Steffen (2006). "ECML-PKDD Discovery Challenge 2006 Overview". ECML-PKDD Discovery Challenge Workshop (PDF). Retrieved 2007-08-05.
  27. ISSN 2169-3536
    .
  28. S2CID 25739012
    .
  29. S2CID 220381239
    .
  30. ^ de Mathelin, Antoine and Deheeger, François and Richard, Guillaume and Mougeot, Mathilde and Vayatis, Nicolas (2020) "ADAPT: Awesome Domain Adaptation Python Toolbox"
  31. ^ Mingsheng Long Junguang Jiang, Bo Fu. (2020) "Transfer-learning-library"
  32. ^ Ke Yan. (2016) "Domain adaptation toolbox"

Sources

Retrieved from "https://en.wikipedia.org/w/index.php?title=Transfer_learning&oldid=1219207936"