Skip to content
Free planNo credit card requiredStart writing
AI for Research home
AI for Research home
Dashboard
Sign inGet started

article · Journal of Physics A Mathematical and Theoretical · 2009

Can a student learn optimally from two different teachers?

Juan Pablo Neirotti

Cited by 5Open access

Abstract

We explore the effects of over-specificity in learning algorithms by investigating the behavior of a student, suited to learn optimally from a teacher B , learning from a teacher B ' ≠ B . We only considered the supervised, on-line learning scenario with teachers selected from a particular family. We found that, in the general case, the application of the optimal algorithm to the wrong teacher produces a residual generalization error, even if the right teacher is harder. By imposing mild conditions to the learning algorithm form, we obtained an approximation for the residual generalization error. Simulations carried out in finite networks validate the estimate found.

Cite this paper

APA 7

Neirotti, J. P. (2009). Can a student learn optimally from two different teachers? Journal of Physics A Mathematical and Theoretical, 43(1), 015101. https://doi.org/10.1088/1751-8113/43/1/015101

MLA 9

Neirotti, Juan Pablo. “Can a student learn optimally from two different teachers?” Journal of Physics A Mathematical and Theoretical, vol. 43, no. 1, 2009, p. 015101, https://doi.org/10.1088/1751-8113/43/1/015101.

Chicago

Neirotti, Juan Pablo. 2009. “Can a student learn optimally from two different teachers?” Journal of Physics A Mathematical and Theoretical 43 (1): 015101. https://doi.org/10.1088/1751-8113/43/1/015101.

Harvard

Neirotti, J.P. (2009) ‘Can a student learn optimally from two different teachers?’, Journal of Physics A Mathematical and Theoretical, 43(1), p. 015101. Available at: https://doi.org/10.1088/1751-8113/43/1/015101.

BibTeX
@article{neirotti2009student,
  title = {{Can a student learn optimally from two different teachers?}},
  author = {Neirotti, Juan Pablo},
  journal = {Journal of Physics A Mathematical and Theoretical},
  volume = {43},
  number = {1},
  pages = {015101},
  year = {2009},
  doi = {10.1088/1751-8113/43/1/015101}
}

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

Related papers