Learn-By-Calibrating: Using Calibration As A Training Objective

This video program is a part of the Premium package:

Learn-By-Calibrating: Using Calibration As A Training Objective


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

Learn-By-Calibrating: Using Calibration As A Training Objective

0 views
  • Share
Create Account or Sign In to post comments
Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not explicitly measure the
Calibration error is commonly adopted for evaluating the quality of uncertainty estimators in deep neural networks. In this paper, we argue that such a metric is highly beneficial for training predictive models, even when we do not explicitly measure the