Information Bottleneck
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...
Na minha lista:
| Formato: | Online |
|---|---|
| Idioma: | inglês |
| Publicado em: |
MDPI - Multidisciplinary Digital Publishing Institute
2022
|
| Assuntos: | |
| Acesso em linha: | ONIX_20220111_9783036508023_165 |
| Tags: |
Sem tags, seja o primeiro a adicionar uma tag!
|
| _version_ | 1869518449920704512 |
|---|---|
| collection | Directory of Open Access Books |
| description | 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. |
| format | Online |
| id | doab-20.500.12854ir-76429 |
| institution | Directory of Open Access Books |
| language | eng |
| publishDate | 2022 |
| publishDateRange | 2022 |
| publishDateSort | 2022 |
| publisher | MDPI - Multidisciplinary Digital Publishing Institute |
| publisherStr | MDPI - Multidisciplinary Digital Publishing Institute |
| record_format | ojs |
| spelling | doab-20.500.12854ir-764292024-03-30T12:51:05Z Information Bottleneck Geiger, Bernhard Kubin, Gernot information theory variational inference machine learning learnability information bottleneck representation learning conspicuous subset stochastic neural networks mutual information neural networks information bottleneck compression classification optimization classifier decision tree ensemble deep neural networks regularization methods information bottleneck principle deep networks semi-supervised classification latent space representation hand crafted priors learnable priors regularization deep learning thema EDItEUR::K Economics, Finance, Business and Management::KN Industry and industrial studies::KNT Media, entertainment, information and communication industries::KNTX Information technology industries 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. 2022-01-11T13:31:40Z 2022-01-11T13:31:40Z 2021 book ONIX_20220111_9783036508023_165 9783036508023 9783036508030 https://directory.doabooks.org/handle/20.500.12854/76429 eng image/jpeg Attribution 4.0 International https://mdpi.com/books/pdfview/book/3864 https://mdpi.com/books/pdfview/book/3864 MDPI - Multidisciplinary Digital Publishing Institute 10.3390/books978-3-0365-0803-0 10.3390/books978-3-0365-0803-0 46cabcaa-dd94-4bfe-87b4-55023c1b36d0 9783036508023 9783036508030 274 Basel, Switzerland open access |
| spellingShingle | information theory variational inference machine learning learnability information bottleneck representation learning conspicuous subset stochastic neural networks mutual information neural networks information bottleneck compression classification optimization classifier decision tree ensemble deep neural networks regularization methods information bottleneck principle deep networks semi-supervised classification latent space representation hand crafted priors learnable priors regularization deep learning thema EDItEUR::K Economics, Finance, Business and Management::KN Industry and industrial studies::KNT Media, entertainment, information and communication industries::KNTX Information technology industries Information Bottleneck |
| title | Information Bottleneck |
| title_full | Information Bottleneck |
| title_fullStr | Information Bottleneck |
| title_full_unstemmed | Information Bottleneck |
| title_short | Information Bottleneck |
| title_sort | information bottleneck |
| topic | information theory variational inference machine learning learnability information bottleneck representation learning conspicuous subset stochastic neural networks mutual information neural networks information bottleneck compression classification optimization classifier decision tree ensemble deep neural networks regularization methods information bottleneck principle deep networks semi-supervised classification latent space representation hand crafted priors learnable priors regularization deep learning thema EDItEUR::K Economics, Finance, Business and Management::KN Industry and industrial studies::KNT Media, entertainment, information and communication industries::KNTX Information technology industries |
| topic_facet | information theory variational inference machine learning learnability information bottleneck representation learning conspicuous subset stochastic neural networks mutual information neural networks information bottleneck compression classification optimization classifier decision tree ensemble deep neural networks regularization methods information bottleneck principle deep networks semi-supervised classification latent space representation hand crafted priors learnable priors regularization deep learning thema EDItEUR::K Economics, Finance, Business and Management::KN Industry and industrial studies::KNT Media, entertainment, information and communication industries::KNTX Information technology industries |
| url | ONIX_20220111_9783036508023_165 |