Search Results for author: Jiří Navrátil

Found 1 papers, 0 papers with code

Confidence Scoring Using Whitebox Meta-models with Linear Classifier Probes

no code implementations14 May 2018 Tongfei Chen, Jiří Navrátil, Vijay Iyengar, Karthikeyan Shanmugam

We propose a novel confidence scoring mechanism for deep neural networks based on a two-model paradigm involving a base model and a meta-model.

Cannot find the paper you are looking for? You can Submit a new open access paper.