The Global Landscape of Neural Networks: An Overview

Ruoyu Sun, Dawei Li, Shiyu Liang, Tian Ding, Rayadurgam Srikant

Research output: Contribution to journalArticlepeer-review

Abstract

One of the major concerns for neural network training is that the nonconvexity of the associated loss functions may cause a bad landscape. The recent success of neural networks suggests that their loss landscape is not too bad, but what specific results do we know about the landscape? In this article, we review recent findings and results on the global landscape of neural networks.

Original languageEnglish (US)
Article number9194023
Pages (from-to)95-108
Number of pages14
JournalIEEE Signal Processing Magazine
Volume37
Issue number5
DOIs
StatePublished - Sep 2020

ASJC Scopus subject areas

  • Signal Processing
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint

Dive into the research topics of 'The Global Landscape of Neural Networks: An Overview'. Together they form a unique fingerprint.

Cite this