Name
Abstract | ||
|---|---|---|
We present a simple case study, demonstrating that Variational Information Bottleneck (VIB) can improve a networku0027s 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. |
Year | Venue | Field |
|---|---|---|
2018 | arXiv: Learning | Mathematical optimization,Algorithm,Information bottleneck method,Calibration,Mathematics |
DocType | Volume | Citations |
Journal | abs/1807.00906 | 9 |
PageRank | References | Authors |
0.50 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alexander A. Alemi | 1 | 70 | 9.92 |
| Ian Fischer | 2 | 422 | 26.82 |
| Joshua V. Dillon | 3 | 50 | 3.85 |