IMPROVING SUPERVISED LEARNING BY ADAPTING THE PROBLEM TO THE LEARNER

Abstract

While no supervised learning algorithm can do well over all functions, we show that it may be possible to adapt a given function to a given supervised learning algorithm so as to allow the learning algorithm to better classify the original function. Although this seems counterintuitive, adapting the problem to the learner may result in an equivalent function that is "easier" for the algorithm to learn. One method of adapting a problem to the learner is to relabel the targets given in the training data. The following presents two problem adaptation methods, SOL-CTR-E and SOL-CTR-P, variants of Self-Oracle Learning with Confidence-based Target Relabeling (SOL-CTR) as a proof of concept for problem adaptation. The SOL-CTR methods produce "easier" target functions for training artificial neural networks (ANNs). Applying SOL-CTR over 41 data sets consistently results in a statistically significant (p < 0.05) improvement in accuracy over 0/1 targets on data sets containing over 10,000 training examples.