To Understand Deep Learning We Need to Understand Kernel Learning
Mikhail Belkin Affiliation: Department of Computer Science and Engineering Siyuan Ma Affiliation: Department of Computer Science and Engineering Soumik Mandal Affiliation: Department of Computer Science and Engineering Affiliation: Ohio State University Affiliation: {mbelkin,
Abstract
Generalization performance of classifiers in deep learning has recently become a subject of intense study. Deep models, which are typically heavily over-parametrized, tend to fit the training data exactly. Despite this “overfitting", they perform well on test data, a phenomenon not yet fully understood.
原文 arXiv:1802.01396;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1802.01396v3