Accuracy-Robustness Trade-Off For Positively Weighted Neural Networks

This video program is a part of the Premium package:

Accuracy-Robustness Trade-Off For Positively Weighted Neural Networks


  • IEEE MemberUS $11.00
  • Society MemberUS $0.00
  • IEEE Student MemberUS $11.00
  • Non-IEEE MemberUS $15.00
Purchase

Accuracy-Robustness Trade-Off For Positively Weighted Neural Networks

0 views
  • Share
This work proposes a new learning strategy for training a feedforward neural network subject to spectral norm and nonnegativity constraints. Our primary goal is to control the Lipschitz constant of the network in order to make it robust against adversaria
This work proposes a new learning strategy for training a feedforward neural network subject to spectral norm and nonnegativity constraints. Our primary goal is to control the Lipschitz constant of the network in order to make it robust against adversaria