article · Wiley Interdisciplinary Reviews Cognitive Science · 2013

Learnability theory

Cited by 5Abstract and details only

Abstract

Learnability theory is a body of mathematical and computational results concerning questions such as: when is learning possible? What prior information is required to support learning? What computational or other resources are required for learning to be possible? It is therefore complementary both to the computational project of building machine learning systems and to the scientific project of understanding learning in people and animals through observation and experiment. Learnability theory includes work within a variety of theoretical frameworks, including, for example, identification in the limit, and Bayesian learning, which idealize learning in different ways. Learnability theory addresses one of the foundational questions in cognitive science: to what extent can knowledge be derived from experience? WIREs Cogn Sci 2013, 4:299-306. doi: 10.1002/wcs.1228 For further resources related to this article, please visit the WIREs website.

Cite this paper

APA 7

Fulop, S. A., & Chater, N. (2013). Learnability theory. Wiley Interdisciplinary Reviews Cognitive Science, 4(3), 299–306. https://doi.org/10.1002/wcs.1228

MLA 9

Fulop, Sean A., and Nick Chater. “Learnability theory.” Wiley Interdisciplinary Reviews Cognitive Science, vol. 4, no. 3, 2013, pp. 299–306, https://doi.org/10.1002/wcs.1228.

Chicago

Fulop, Sean A., and Nick Chater. 2013. “Learnability theory.” Wiley Interdisciplinary Reviews Cognitive Science 4 (3): 299–306. https://doi.org/10.1002/wcs.1228.

Harvard

Fulop, S.A. and Chater, N. (2013) ‘Learnability theory’, Wiley Interdisciplinary Reviews Cognitive Science, 4(3), pp. 299–306. Available at: https://doi.org/10.1002/wcs.1228.

BibTeX

@article{fulop2013learnability,
  title = {{Learnability theory}},
  author = {Fulop, Sean A. and Chater, Nick},
  journal = {Wiley Interdisciplinary Reviews Cognitive Science},
  volume = {4},
  number = {3},
  pages = {299--306},
  year = {2013},
  doi = {10.1002/wcs.1228}
}

Made from the index record. Check names, capitalisation and page numbers against the paper. Need another style? AI for Research has over 10,000.