Can I read Realizing Data Features by Deep Nets on EtoBox?

Realizing Data Features by Deep Nets by Guo, Zheng-Chu; Shi, Lei; Lin, Shao-Bo is a scholarly article available to read on EtoBox.

What is Realizing Data Features by Deep Nets about?

This paper considers the power of deep neural networks (deep nets for short) in realizing data features. Based on refined covering number estimates, we find that, to realize some complex data features, deep nets can improve the performances of shallow neural networks (shallow nets for short) without requiring additional capacity costs. This verifies the advantage of deep nets in realizing complex features. On the other hand, to realize some simple data feature like the smoothness, we prove that, up to a logarithmic factor, the approximation rate of deep nets is asymptotically identical to that of shallow nets, provided that the depth is fixed. This exhibits a limitation of deep nets in realizing simple features.

Author

Guo, Zheng-Chu; Shi, Lei; Lin, Shao-Bo

Published

2019

Language

EN