000 03085naaaa2200649uu 4500
001 https://directory.doabooks.org/handle/20.500.12854/76429
005 20220219212126.0
020 _abooks978-3-0365-0803-0
020 _a9783036508023
020 _a9783036508030
024 7 _a10.3390/books978-3-0365-0803-0
_cdoi
041 0 _aEnglish
042 _adc
072 7 _aKNTX
_2bicssc
100 1 _aGeiger, Bernhard
_4edt
700 1 _aKubin, Gernot
_4edt
700 1 _aGeiger, Bernhard
_4oth
700 1 _aKubin, Gernot
_4oth
245 1 0 _aInformation Bottleneck : Theory and Applications in Deep Learning
260 _aBasel, Switzerland
_bMDPI - Multidisciplinary Digital Publishing Institute
_c2021
300 _a1 electronic resource (274 p.)
506 0 _aOpen Access
_2star
_fUnrestricted online access
520 _aThe 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 _aCreative Commons
_fhttps://creativecommons.org/licenses/by/4.0/
_2cc
_4https://creativecommons.org/licenses/by/4.0/
546 _aEnglish
650 7 _aInformation technology industries
_2bicssc
653 _ainformation theory
653 _avariational inference
653 _amachine learning
653 _alearnability
653 _ainformation bottleneck
653 _arepresentation learning
653 _aconspicuous subset
653 _astochastic neural networks
653 _amutual information
653 _aneural networks
653 _ainformation
653 _abottleneck
653 _acompression
653 _aclassification
653 _aoptimization
653 _aclassifier
653 _adecision tree
653 _aensemble
653 _adeep neural networks
653 _aregularization methods
653 _ainformation bottleneck principle
653 _adeep networks
653 _asemi-supervised classification
653 _alatent space representation
653 _ahand crafted priors
653 _alearnable priors
653 _aregularization
653 _adeep learning
856 4 0 _awww.oapen.org
_uhttps://mdpi.com/books/pdfview/book/3864
_70
_zDOAB: download the publication
856 4 0 _awww.oapen.org
_uhttps://directory.doabooks.org/handle/20.500.12854/76429
_70
_zDOAB: description of the publication
999 _c44560
_d44560