Multitask Learning

  title={Multitask Learning},
  author={Rich Caruana},
  journal={Machine Learning},
Multitask Learning is an approach to inductive transfer that improves generalization by using the domain information contained in the training signals of related tasks as an inductive bias. It does this by learning tasks in parallel while using a shared representation; what is learned for each task can help other tasks be learned better. This paper reviews prior work on MTL, presents new evidence that MTL in backprop nets discovers task relatedness without the need of supervisory signals, and… CONTINUE READING
Highly Influential
This paper has highly influenced 190 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 3,511 citations. REVIEW CITATIONS
1,714 Citations
55 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 1,714 extracted citations

3,512 Citations

Citations per Year
Semantic Scholar estimates that this publication has 3,512 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 55 references

An Evaluation of Machine Learning Methods for Predicting Pneumonia Mortality,

  • G. Gordon, B. H. Hanusa, +4 authors P. Spirtes
  • Artificial Intelligence in Medicine
  • 1997

Multitask Learning,

  • R. Caruana
  • Ph.D. Thesis,
  • 1997
2 Excerpts

Goal-directed Clustering,

  • J D.
  • 13th International Conference on Machine Learning…
  • 1996

Similar Papers

Loading similar papers…