papers AI Learner
The Github is limit! Click to go to the new site.

Generalization in Deep Learning

2019-01-01
Kenji Kawaguchi, Leslie Pack Kaelbling, Yoshua Bengio

Abstract

Throughout this chapter, we provide theoretical insights into why and how deep learning can generalize well, despite its large capacity, complexity, possible algorithmic instability, nonrobustness, and sharp minima, responding to an open question in the literature. We also propose new open problems and discuss the limitations of our results.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1710.05468

PDF

http://arxiv.org/pdf/1710.05468


Similar Posts

Comments