Transfer learning

Quality 0.50 · 1 view · Updated 2 months ago

Machine learning technique

title: "Transfer learning" type: doc version: 1 created: 2026-02-28 author: "Wikipedia contributors" status: active scope: public tags: ["machine-learning"] description: "Machine learning technique" topic_path: "technology/computing" source: "https://en.wikipedia.org/wiki/Transfer_learning" license: "CC BY-SA 4.0" wikipedia_page_id: 0 wikipedia_revision_id: 0

::summary Machine learning technique ::

::figure[src="https://upload.wikimedia.org/wikipedia/commons/6/6f/Transfer_learning.svg" caption="Illustration of transfer learning"] ::

Transfer learning (TL) is a technique in machine learning (ML) in which knowledge learned from a task is re-used in order to boost performance on a related task. For example, for 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 or transferring information from previously learned tasks to new tasks has the potential to significantly improve learning efficiency.

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

History

In 1976, Bozinovski and Fulgosi published a paper addressing transfer learning in neural network training. 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.

In 1992, Lorien Pratt formulated the discriminability-based transfer (DBT) algorithm.

By 1998, the field had advanced to include multi-task learning, along with more formal theoretical foundations. Influential publications on transfer learning include the book Learning to Learn in 1998, a 2009 survey and a 2019 survey.

Ng said in his NIPS 2016 tutorial 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", Zoph et al. reported that pre-training can hurt accuracy, and advocate self-training instead.

Definition

The definition of transfer learning is given in terms of domains and tasks. A domain \mathcal{D} consists of: a feature space \mathcal{X} and a marginal probability distribution P(X), where X = {x_1,...,x_n} \in \mathcal{X}. Given a specific domain, \mathcal{D} = {\mathcal{X}, P(X)}, a task consists of two components: a label space \mathcal{Y} and an objective predictive function f:\mathcal{X} \rightarrow \mathcal{Y} . The function f is used to predict the corresponding label f(x) of a new instance x. This task, denoted by \mathcal{T} = {\mathcal{Y}, f(x)}, is learned from the training data consisting of pairs {x_i, y_i}, where x_i \in \mathcal{X} and y_i \in \mathcal{Y}.

Given a source domain \mathcal{D}_S and learning task \mathcal{T}_S, a target domain \mathcal{D}_T and learning task \mathcal{T}_T, where \mathcal{D}_S \neq \mathcal{D}_T, or \mathcal{T}_S \neq \mathcal{T}_T, transfer learning aims to help improve the learning of the target predictive function f_T (\cdot) in \mathcal{D}_T using the knowledge in \mathcal{D}_S and \mathcal{T}_S.

Applications

Algorithms for transfer learning are available in Markov logic networks and Bayesian networks. Transfer learning has been applied to cancer subtype discovery, building utilization, general game playing, text classification, digit recognition, medical imaging and spam filtering.

In 2020, it was discovered that, due to their similar physical natures, transfer learning is possible between electromyographic (EMG) signals from the muscles and classifying the behaviors of electroencephalographic (EEG) brainwaves, from the gesture recognition domain to the mental state recognition domain. It was noted that this relationship worked in both directions, showing that electroencephalographic can likewise be used to classify EMG. The experiments noted that the accuracy of neural networks and convolutional neural networks were improved 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.

References

Sources

References

  1. (2007). "Spring Research Presentation: A Theoretical Foundation for Inductive Transfer". Brigham Young University, College of Physical and Mathematical Sciences.
  2. (2019). "Self-organizing maps for storage and transfer of knowledge in reinforcement learning". Adaptive Behavior.
  3. Cost-Sensitive Machine Learning. (2011). USA: CRC Press, Page 63, https://books.google.com/books?id=8TrNBQAAQBAJ&pg=PA63
  4. Stevo. Bozinovski and Ante Fulgosi (1976). "The influence of pattern similarity and transfer learning on the base perceptron training." (original in Croatian) Proceedings of Symposium Informatica 3-121-5, Bled.
  5. Stevo Bozinovski (2020) [https://www.informatica.si/index.php/informatica/article/viewFile/2828/1433 "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 [https://web.cs.umass.edu/publication/docs/1981/UM-CS-1981-028.pdf online]]
  7. Pratt, L. Y.. (1992). ["NIPS Conference: Advances in Neural Information Processing Systems 5"]({{google books). Morgan Kaufmann Publishers.
  8. Caruana, R., "Multitask Learning", pp. 95-134 in {{Harvnb. Thrun. Pratt. 2012
  9. Baxter, J., "Theoretical Models of Learning to Learn", pp. 71-95 {{Harvnb. Thrun. Pratt. 2012
  10. (2010). "A Survey on Transfer Learning". IEEE Transactions on Knowledge and Data Engineering.
  11. (2019). "A Comprehensive Survey on Transfer Learning".
  12. (6 May 2018). "NIPS 2016 tutorial: "Nuts and bolts of building AI applications using Deep Learning" by Andrew Ng".
  13. "Nuts and bolts of building AI applications using Deep Learning, slides".
  14. (2020). "Rethinking pre-training and self-training". Advances in Neural Information Processing Systems.
  15. (27 June 2017). "Improving EEG-Based Emotion Classification Using Conditional Transfer Learning". Frontiers in Human Neuroscience.
  16. (July 2007). "Learning Proceedings of the 22nd AAAI Conference on Artificial Intelligence (AAAI-2007)".
  17. (March 21–24, 2007). "Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics (AISTATS 2007)".
  18. Hajiramezanali, E. & Dadaneh, S. Z. & Karbalayghareh, A. & Zhou, Z. & Qian, X. Bayesian multi-domain learning for cancer subtype discovery from next-generation sequencing count data. 32nd Conference on Neural Information Processing Systems (NeurIPS 2018), Montréal, Canada. {{arXiv. 1810.09433
  19. (2017-11-08). "DA-HOC: semi-supervised domain adaptation for room occupancy prediction using CO2 sensor data".
  20. (2018-12-01). "A Scalable Room Occupancy Prediction with Transferable Time Series Decomposition of CO2 Sensor Data". ACM Transactions on Sensor Networks.
  21. Banerjee, Bikramjit, and Peter Stone. "[http://www.aaai.org/Papers/IJCAI/2007/IJCAI07-107.pdf General Game Learning Using Knowledge Transfer]." IJCAI. 2007.
  22. (2005). "Neural Information Processing Systems Foundation, NIPS*2005".
  23. (2006). "Twenty-third International Conference on Machine Learning".
  24. (August 2015). "2015 13th International Conference on Document Analysis and Recognition (ICDAR)".
  25. Bickel, Steffen. (2006). "ECML-PKDD Discovery Challenge Workshop".
  26. (2020). "Cross-Domain MLP and CNN Transfer Learning for Biological Signal Processing: EEG and EMG". Institute of Electrical and Electronics Engineers (IEEE).
  27. (August 2015). "2015 13th International Conference on Document Analysis and Recognition (ICDAR)".
  28. (January 7, 2022). "SpinalNet: Deep Neural Network with Gradual Input". IEEE Transactions on Artificial Intelligence.

::callout[type=info title="Wikipedia Source"] This article was imported from Wikipedia and is available under the Creative Commons Attribution-ShareAlike 4.0 License. Content has been adapted to SurfDoc format. Original contributors can be found on the article history page. ::

machine-learning