1995
@techreport{WLZ1995,
vgclass = {report},
vgproject = {nn},
author = {O. Winther and B. Lautrup and J-B. Zhang},
title = {Optimal Learning in Multilayer Neural Networks},
number = {95-200},
institution = {CERN, Theory Division},
address = {1211 Gen\`{e}ve 23, Switzerland},
month = {August},
year = {1995},
abstract = {The generalization performance of two learning algorithms,
Bayes algorithm and the ``optimal learning'' algorithm on two
classification tasks is studied theoretically. In the first example the
task is defined by a restricted two-layer network, a committee machine,
and in the second the task is defined by the so-called prototype
problem. The architecture of the learning machine is in both cases
defined to be a committee machine. For both tasks the optimal learning
algorithm, which is optimal when the solution is restricted to a
specific architecture, performs worse than the overall optimal Bayes
algorithm. However, both algorithms perform far better than the
conventional stochastic Gibbs algorithm, showing that using prior
knowledge about the rule helps to avoid overfitting.},
}