01060cam0 2200277 450 E60020001863920210215150654.020060607d1935 |||||ita|0103 baitaITAutobiografiaBeniamino Franklinprefazione e note di Gino ValoriMilanoEd. I. T. E.c1935231 p.20 cmCollana di autobiografie dei più illustri uomini del mondo001LAEC000223102001 *Collana di autobiografie dei più illustri uomini del mondoFranklin, BenjaminA60020003659307056881Valori, GinoA600200036594070ITUNISOB20210215RICAUNISOBUNISOB900130226E600200018639M 102 Monografia moderna SBNM900004516Si130226donocatenacciUNISOBUNISOB20060607095654.020210215150654.0rovitoTit.orig.:The autobiography of Beniamin Franklin - traduzione di Patrizia Paggio22239UNISOB02997nam 2200709z- 450 991055758280332120220111(CKB)5400000000043820(oapen)https://directory.doabooks.org/handle/20.500.12854/76429(oapen)doab76429(EXLCZ)99540000000004382020202201d2021 |y 0engurmn|---annantxtrdacontentcrdamediacrrdacarrierInformation BottleneckTheory and Applications in Deep LearningBasel, SwitzerlandMDPI - Multidisciplinary Digital Publishing Institute20211 online resource (274 p.)3-0365-0802-3 3-0365-0803-1 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.Information Bottleneck Information technology industriesbicsscbottleneckclassificationclassifiercompressionconspicuous subsetdecision treedeep learningdeep networksdeep neural networksensemblehand crafted priorsinformationinformation bottleneckinformation bottleneck principleinformation theorylatent space representationlearnabilitylearnable priorsmachine learningmutual informationneural networksoptimizationregularizationregularization methodsrepresentation learningsemi-supervised classificationstochastic neural networksvariational inferenceInformation technology industriesGeiger Bernhardedt640524Kubin GernotedtGeiger BernhardothKubin GernotothBOOK9910557582803321Information Bottleneck3025092UNINA