LEADER 02982nam 2200697z- 450 001 9910557582803321 005 20231214133530.0 035 $a(CKB)5400000000043820 035 $a(oapen)https://directory.doabooks.org/handle/20.500.12854/76429 035 $a(EXLCZ)995400000000043820 100 $a20202201d2021 |y 0 101 0 $aeng 135 $aurmn|---annan 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 10$aInformation Bottleneck$eTheory and Applications in Deep Learning 210 $aBasel, Switzerland$cMDPI - Multidisciplinary Digital Publishing Institute$d2021 215 $a1 electronic resource (274 p.) 311 $a3-0365-0802-3 311 $a3-0365-0803-1 330 $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. 517 $aInformation Bottleneck 606 $aInformation technology industries$2bicssc 610 $ainformation theory 610 $avariational inference 610 $amachine learning 610 $alearnability 610 $ainformation bottleneck 610 $arepresentation learning 610 $aconspicuous subset 610 $astochastic neural networks 610 $amutual information 610 $aneural networks 610 $ainformation 610 $abottleneck 610 $acompression 610 $aclassification 610 $aoptimization 610 $aclassifier 610 $adecision tree 610 $aensemble 610 $adeep neural networks 610 $aregularization methods 610 $ainformation bottleneck principle 610 $adeep networks 610 $asemi-supervised classification 610 $alatent space representation 610 $ahand crafted priors 610 $alearnable priors 610 $aregularization 610 $adeep learning 615 7$aInformation technology industries 700 $aGeiger$b Bernhard$4edt$0640524 702 $aKubin$b Gernot$4edt 702 $aGeiger$b Bernhard$4oth 702 $aKubin$b Gernot$4oth 906 $aBOOK 912 $a9910557582803321 996 $aInformation Bottleneck$93025092 997 $aUNINA