Login / Signup
Critical Point-Finding Methods Reveal Gradient-Flat Regions of Deep Network Losses.
Charles G. Frye
James Simon
Neha S. Wadia
Andrew Ligeralde
Michael Robert DeWeese
Kristofer E. Bouchard
Published in:
CoRR (2020)
Keyphrases
</>
computational cost
significant improvement
critical points
machine learning
pattern recognition
principal component analysis
machine learning methods
network model
data sets
neural network
medical images
level set
benchmark datasets
computer networks