Google Research

Uncertainty in the Variational Information Bottleneck

(2018)

Abstract

Without explictly being designed to do so, VIB (Alemi et al., 2017) gives two natural metrics for handling and quantifying uncertainty in neural networks. In this work we present a simple case study, demonstrating that VIB can improve a networks classification calibration as well as its ability to detect out of sample data.

Research Areas

Learn more about how we do research

We maintain a portfolio of research projects, providing individuals and teams the freedom to emphasize specific types of work