Machine Learning: From Theory to Applications: Cooperative Research at Siemens and MIT (Lecture Notes in Computer Science, Band 661) Cooperative Research at Siemens and MIT

Hanson, Stephen J., Werner Remmele and Ronald L. Rivest

ISBN 10: 3540564837 / ISBN 13: 9783540564836

Editore: Springer 13.06.2008., 2008

Riguardo questo articolo

288 Seiten Exemplar aus einer wissenchaftlichen Bibliothek Altersfreigabe FSK ab 0 Jahre Sprache: Englisch Gewicht in Gramm: 969 23,5 x 1,5 x 1,7 cm, Taschenbuch. Codice articolo 401888

Dati bibliografici

Titolo: Machine Learning: From Theory to ...

Casa editrice: Springer 13.06.2008.

Data di pubblicazione: 2008

Legatura: Brossura

Condizione: Gut

Edizione: Auflage: 1993.

Descrizione articolo

Riassunto:

This volume includes some of the key research papers in thearea of machine learning produced at MIT and Siemens duringa three-year joint research effort. It includes papers onmany different styles of machine learning, organized intothree parts.Part I, theory, includes three papers on theoretical aspectsof machine learning. The first two use the theory ofcomputational complexity to derive some fundamental limitson what isefficiently learnable. The third provides anefficient algorithm for identifying finite automata.Part II, artificial intelligence and symbolic learningmethods, includes five papers giving an overview of thestate of the art and future developments in the field ofmachine learning, a subfield of artificial intelligencedealing with automated knowledge acquisition and knowledgerevision.Part III, neural and collective computation, includes fivepapers sampling the theoretical diversity and trends in thevigorous new research field of neural networks: massivelyparallel symbolic induction, task decomposition throughcompetition, phoneme discrimination, behavior-basedlearning, and self-repairing neural networks.

Contenuti:

Strategic directions in machine learning.- Training a 3-node neural network is NP-complete.- Cryptographic limitations on learning Boolean formulae and finite automata.- Inference of finite automata using homing sequences.- Adaptive search by learning from incomplete explanations of failures.- Learning of rules for fault diagnosis in power supply networks.- Cross references are features.- The schema mechanism.- L-ATMS: A tight integration of EBL and the ATMS.- Massively parallel symbolic induction of protein structure/function relationships.- Task decomposition through competition in a modular connectionist architecture: The what and where vision tasks.- Phoneme discrimination using connectionist networks.- Behavior-based learning to control IR oven heating: Preliminary investigations.- Trellis codes, receptive fields, and fault tolerant, self-repairing neural networks.