Fast Weak Learner Based on Genetic Algorithm

TL;DR

This paper introduces a genetic algorithm-based method to accelerate the training of parametric weak classifiers in boosting, significantly reducing training time while maintaining low errors.

Contribution

It presents a novel approach using genetic algorithms for parametric weak classifier training, improving speed over traditional exhaustive search methods.

Findings

Training time is dramatically decreased.

Both training and test errors remain low.

Effective for classifiers with existing learning algorithms.

Abstract

An approach to the acceleration of parametric weak classifier boosting is proposed. Weak classifier is called parametric if it has fixed number of parameters and, so, can be represented as a point into multidimensional space. Genetic algorithm is used instead of exhaustive search to learn parameters of such classifier. Proposed approach also takes cases when effective algorithm for learning some of the classifier parameters exists into account. Experiments confirm that such an approach can dramatically decrease classifier training time while keeping both training and test errors small.