LEADER 01007nam0-22003251i-450- 001 990003871580403321 005 20080128121048.0 010 $a1-898128-53-7 035 $a000387158 035 $aFED01000387158 035 $a(Aleph)000387158FED01 035 $a000387158 100 $a20030910d2000----km-y0itay50------ba 101 0 $aeng 200 1 $aAsset Prices and Central Bank Policy$fStephen G. Cecchetti...[et al.] 210 $aGeneva$cCEPR$d2000 215 $axx, 140 p.$cill.$d25 cm 225 1 $aGeneva reports on the world economy$v2 610 0 $aInflazione 610 0 $aInflazione e politica monetaria 700 1$aCecchetti,$bStephen G.$0146851 712 02$aInternational Center for Monetary and Banking Studies 712 02$aCentre for economic policy research 801 0$aIT$bUNINA$gRICA$2UNIMARC 901 $aBK 912 $a990003871580403321 952 $aJ/2.12 CEC$b19079$fSES 959 $aSES 996 $aAsset Prices and Central Bank Policy$9514302 997 $aUNINA LEADER 02997nam 2200709z- 450 001 9910557582803321 005 20220111 035 $a(CKB)5400000000043820 035 $a(oapen)https://directory.doabooks.org/handle/20.500.12854/76429 035 $a(oapen)doab76429 035 $a(EXLCZ)995400000000043820 100 $a20202201d2021 |y 0 101 0 $aeng 135 $aurmn|---annan 181 $ctxt$2rdacontent 182 $cc$2rdamedia 183 $acr$2rdacarrier 200 00$aInformation Bottleneck$eTheory and Applications in Deep Learning 210 $aBasel, Switzerland$cMDPI - Multidisciplinary Digital Publishing Institute$d2021 215 $a1 online resource (274 p.) 311 08$a3-0365-0802-3 311 08$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 $abottleneck 610 $aclassification 610 $aclassifier 610 $acompression 610 $aconspicuous subset 610 $adecision tree 610 $adeep learning 610 $adeep networks 610 $adeep neural networks 610 $aensemble 610 $ahand crafted priors 610 $ainformation 610 $ainformation bottleneck 610 $ainformation bottleneck principle 610 $ainformation theory 610 $alatent space representation 610 $alearnability 610 $alearnable priors 610 $amachine learning 610 $amutual information 610 $aneural networks 610 $aoptimization 610 $aregularization 610 $aregularization methods 610 $arepresentation learning 610 $asemi-supervised classification 610 $astochastic neural networks 610 $avariational inference 615 7$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