Fractal Dimension Generalization Measure
Machine Learning
2020-12-24 v1 Machine Learning
Abstract
Developing a robust generalization measure for the performance of machine learning models is an important and challenging task. A lot of recent research in the area focuses on the model decision boundary when predicting generalization. In this paper, as part of the "Predicting Generalization in Deep Learning" competition, we analyse the complexity of decision boundaries using the concept of fractal dimension and develop a generalization measure based on that technique.
Cite
@article{arxiv.2012.12384,
title = {Fractal Dimension Generalization Measure},
author = {Valeri Alexiev},
journal= {arXiv preprint arXiv:2012.12384},
year = {2020}
}
Comments
4 pages, 2 figures, presented at the "Predicting Generalization in Deep Learning" competition at NeurIPS 2020