Towards Understanding Generalization via Analytical Learning Theory

Towards Understanding Generalization via Analytical Learning Theory

This paper introduces a novel measure-theoretic theory for machine learning that does not require statistical assumptions. Based on this theory, a new regularization method in deep learning is derived and shown to outperform previous methods in CIFAR-10, CIFAR-100, and SVHN. Moreover, the propose...

Full description

Bibliographic Details
Main Authors: Kawaguchi, Kenji, Benigo, Yoshua, Verma, Vikas, Kaelbling, Leslie Pack
Format: Article
Language:en_US
Published: 2018
Subjects:
Machine Learning
Measure Theory
Regularization method
Neural Network
Online Access:http://hdl.handle.net/1721.1/118307

Internet

http://hdl.handle.net/1721.1/118307

Similar Items