资源分类
》 资源 》论文》TRUTH OR BACKPROPAGANDA ?A NEMPIRICAL IN -VESTIGATION OF DEEP LEARNING THEORY

TRUTH OR BACKPROPAGANDA ?A NEMPIRICAL IN -VESTIGATION OF DEEP LEARNING THEORY

2020-01-02 | |  58 |   42 |   0

Abstract

We empirically evaluate common assumptions about neural networks that are widely held by practitioners and theorists alike. We study the prevalence of local minima in loss landscapes, whether small-norm parameter vectors generalize better (and whether this explains the advantages of weight decay), whether widenetwork theories (like the neural tangent kernel) describe the behaviors of classifiers, and whether the rank of weight matrices can be linked to generalization and robustness in real-world networks.

上一篇：SYNTHESIZING PROGRAMMATIC POLICIES THAT IN-DUCTIVELY GENERALIZE

下一篇：A THEORY OF USABLE INFORMATION UNDER COMPU -TATIONAL CONSTRAINTS

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...