Information Bottleneck: Theory and Applications in Deep Learning

被引：9

作者：

Geiger, Bernhard C. ^{[1
]}

Kubin, Gernot ^{[2
]}

机构：

[1] Know Ctr GmbH, Inffeldgasse 13-6, A-8010 Graz, Austria

[2] Graz Univ Technol, Signal Proc & Speech Commun Lab, Inffeldgasse 16c, A-8010 Graz, Austria

来源：

基金：

欧盟地平线“2020”;

关键词：

information bottleneck; deep learning; neural networks;

D O I：

10.3390/e22121408

中图分类号：

O4 [物理学];

学科分类号：

0702 ;

摘要：

引用

页数：4

共 22 条

[1] Information Dropout: Learning Optimal Representations Through Noisy Computation
Achille, Alessandro
Soatto, Stefano
[J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (12) : 2897 - 2905
[2] Alemi A. A., 2017, P INT C LEARN REPR I
[3] [Anonymous], 2020, ENTROPY SWITZ, DOI DOI 10.3390/E22020151
[4] [Anonymous], 2020, ENTROPY SWITZ, DOI DOI 10.3390/e22090999
[5] Belghazi MI, 2018, PR MACH LEARN RES, V80
[6] FISCHER I, 2020, ENTROPY-SWITZ, V22, DOI DOI 10.3390/e22101081
[7] Probabilistic Ensemble of Deep Information Networks
Franzese, Giulio
Visintin, Monica
[J]. ENTROPY, 2020, 22 (01) : 100
[8] The Convex Information Bottleneck Lagrangian
Galvez, Borja Rodriguez
Thobaben, Ragnar
Skoglund, Mikael
[J]. ENTROPY, 2020, 22 (01) : 98
[9] Geiger B. C., 2020, ARXIV200309671
[10] GEIGER BC, 2020, ENTROPY-SWITZ, V22, DOI DOI 10.3390/e22111229