2012 International Conference on Information and Automation

• Record Nr.: UNISA996207348503316
• Pubbl/distr/stampa: [Place of publication not identified], : IEEE, 2012
• ISBN: 1-4673-2237-7; 1-4673-2236-9
• Descrizione fisica: 1 online resource (998 pages)
• Disciplina: 629.892
• Soggetti: Robots - Control systems
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: Bibliographic Level Mode of Issuance: Monograph
• Nota di bibliografia: Includes bibliographical references and index.

Information Bottleneck : Theory and Applications in Deep Learning

• Record Nr.: UNINA9910557582803321
• Autore: Geiger Bernhard
• Pubbl/distr/stampa: Basel, Switzerland, : MDPI - Multidisciplinary Digital Publishing Institute, 2021
• Descrizione fisica: 1 online resource (274 p.)
• Soggetti: Information technology industries
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Sommario/riassunto: 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.