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.
|Number of pages||1|
|Journal||Journal of Physics A: Mathematical and Theoretical|
|Publication status||Published - 2010|
Bibliographical note© 2010 IOP Publishing Ltd.
- over-specificity in learning algorithms
- the supervised
- on-line learning scenario
- optimal algorithm
- residual generalization error simulations
- finite networks