Information Bottleneck Theory and Applications in Deep Learning
The celebrated information bottleneck (IB) principle of Tishby et al. has recently enjoyed renewed attention due to its application in the area of deep learning. This collection investigates the IB principle in this new context. The individual chapters in this collection: • provide novel insights in...
Saved in:
Other Authors: | , |
---|---|
Format: | Electronic Book Chapter |
Language: | English |
Published: |
Basel, Switzerland
MDPI - Multidisciplinary Digital Publishing Institute
2021
|
Subjects: | |
Online Access: | DOAB: download the publication DOAB: description of the publication |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
MARC
LEADER | 00000naaaa2200000uu 4500 | ||
---|---|---|---|
001 | doab_20_500_12854_76429 | ||
005 | 20220111 | ||
003 | oapen | ||
006 | m o d | ||
007 | cr|mn|---annan | ||
008 | 20220111s2021 xx |||||o ||| 0|eng d | ||
020 | |a books978-3-0365-0803-0 | ||
020 | |a 9783036508023 | ||
020 | |a 9783036508030 | ||
040 | |a oapen |c oapen | ||
024 | 7 | |a 10.3390/books978-3-0365-0803-0 |c doi | |
041 | 0 | |a eng | |
042 | |a dc | ||
072 | 7 | |a KNTX |2 bicssc | |
100 | 1 | |a Geiger, Bernhard |4 edt | |
700 | 1 | |a Kubin, Gernot |4 edt | |
700 | 1 | |a Geiger, Bernhard |4 oth | |
700 | 1 | |a Kubin, Gernot |4 oth | |
245 | 1 | 0 | |a Information Bottleneck |b Theory and Applications in Deep Learning |
260 | |a Basel, Switzerland |b MDPI - Multidisciplinary Digital Publishing Institute |c 2021 | ||
300 | |a 1 electronic resource (274 p.) | ||
336 | |a text |b txt |2 rdacontent | ||
337 | |a computer |b c |2 rdamedia | ||
338 | |a online resource |b cr |2 rdacarrier | ||
506 | 0 | |a Open Access |2 star |f Unrestricted online access | |
520 | |a The celebrated information bottleneck (IB) principle of Tishby et al. has recently enjoyed renewed attention due to its application in the area of deep learning. This collection investigates the IB principle in this new context. The individual chapters in this collection: • provide novel insights into the functional properties of the IB; • discuss the IB principle (and its derivates) as an objective for training multi-layer machine learning structures such as neural networks and decision trees; and • offer a new perspective on neural network learning via the lens of the IB framework. Our collection thus contributes to a better understanding of the IB principle specifically for deep learning and, more generally, of information-theoretic cost functions in machine learning. This paves the way toward explainable artificial intelligence. | ||
540 | |a Creative Commons |f https://creativecommons.org/licenses/by/4.0/ |2 cc |4 https://creativecommons.org/licenses/by/4.0/ | ||
546 | |a English | ||
650 | 7 | |a Information technology industries |2 bicssc | |
653 | |a information theory | ||
653 | |a variational inference | ||
653 | |a machine learning | ||
653 | |a learnability | ||
653 | |a information bottleneck | ||
653 | |a representation learning | ||
653 | |a conspicuous subset | ||
653 | |a stochastic neural networks | ||
653 | |a mutual information | ||
653 | |a neural networks | ||
653 | |a information | ||
653 | |a bottleneck | ||
653 | |a compression | ||
653 | |a classification | ||
653 | |a optimization | ||
653 | |a classifier | ||
653 | |a decision tree | ||
653 | |a ensemble | ||
653 | |a deep neural networks | ||
653 | |a regularization methods | ||
653 | |a information bottleneck principle | ||
653 | |a deep networks | ||
653 | |a semi-supervised classification | ||
653 | |a latent space representation | ||
653 | |a hand crafted priors | ||
653 | |a learnable priors | ||
653 | |a regularization | ||
653 | |a deep learning | ||
856 | 4 | 0 | |a www.oapen.org |u https://mdpi.com/books/pdfview/book/3864 |7 0 |z DOAB: download the publication |
856 | 4 | 0 | |a www.oapen.org |u https://directory.doabooks.org/handle/20.500.12854/76429 |7 0 |z DOAB: description of the publication |