Uncertainty in the Variational Information Bottleneck. (arXiv:1807.00906v1 [cs.LG])

We present a simple case study, demonstrating that Variational Information Bottleneck (VIB) can improve a network's classification calibration as well as its ability to detect out-of-distribution data. Without explicitly being designed to do so, VIB gives two natural metrics for handling and quantifying uncertainty.

from cs updates on arXiv.org https://ift.tt/2IPFyMO
//