Answers are grounded in this paper and cite their sources.
Learning of realizable rules is studied for tree committee machines with continuous weights. No nontrivial upper bound exists for the generalization error of consistent students as the number of hidden units K increases. However, numerical considerations show that consistent students with a value of the generalization error significantly higher than predicted by the average case analysis are extremely hard to find. An online learning algorithm is presented, for which the generalization error scales with the training set size as in the average case theory in the limit of large K. PACS: 87.10,05.50,64.60C. In recent years there has been great interest in making theoretical predictions on the possibility of inferring a rule from examples. In one of the simpler scenarios, we know exactly what kind of deterministic rule we are looking for. So given a set of boolean functions F on a domain \Ω\Γ the target rule or teacher ~ f is just an element of F . We cannot observe ~ f directly,...
No takes yet. Share an insight, caveat, or question.
Robert Urbanczik (1996) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: