Abstract | ||
---|---|---|
In this preliminary work, we study the generalization properties of infinite ensembles of infinitely-wide neural networks. Amazingly, this model family admits tractable calculations for many information-theoretic quantities. We report analytical and empirical investigations in the search for signals that correlate with generalization. |
Year | Venue | DocType |
---|---|---|
2019 | AABI | Conference |
Citations | PageRank | References |
0 | 0.34 | 0 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Schwartz-Ziv Ravid | 1 | 0 | 0.34 |
Alexander A. Alemi | 2 | 70 | 9.92 |
Ravid Shwartz-Ziv | 3 | 115 | 4.27 |