Abstract | ||
---|---|---|
•We propose a new concept of information capacity regularization in deep neural networks.•An information loss penalty for regularization of binary neural networks is developed.•Experiments were conducted with today’s best performing techniques.•Information loss penalty boosts the accuracy of existing state-of-the-art binary networks.•We statistically prove the efficiency of the new regularization approach on 4 common datasets. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1016/j.patrec.2020.07.033 | Pattern Recognition Letters |
Keywords | DocType | Volume |
Deep learning,Binary neural network,Information theory,Shannon entropy | Journal | 138 |
ISSN | Citations | PageRank |
0167-8655 | 2 | 0.36 |
References | Authors | |
24 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dmitry Ignatov | 1 | 2 | 0.36 |
Andrey Ignatov | 2 | 30 | 6.66 |