{"product_id":"9781461374930","title":"The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar","description":"\u003ch1\u003eThe Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar\u003c\/h1\u003e \u003ch2\u003eNiyogi, Partha\u003c\/h2\u003e \u003cp\u003eAmong other topics, \u003cem\u003eThe Informational Complexity of  Learning:\u003c\/em\u003e \u003cem\u003ePerspectives on Neural Networks and Generative  Grammar\u003c\/em\u003e brings together two important but very different learning  problems within the same analytical framework. The first concerns the  problem of learning functional mappings using neural networks,  followed by learning natural language grammars in the principles and  parameters tradition of Chomsky. \u003cbr\u003e  These two learning problems are seemingly very different. Neural  networks are real-valued, infinite-dimensional, continuous mappings.  On the other hand, grammars are boolean-valued, finite-dimensional,  discrete (symbolic) mappings. Furthermore the research communities  that work in the two areas almost never overlap. \u003cbr\u003e  The book's objective is to bridge this gap. It uses the formal  techniques developed in statistical learning theory and theoretical  computer science over the last decade to analyze both kinds of  learning problems. By asking the same question - how much  information does it take to learn? - of both problems, it  highlights their similarities and differences. Specific results  include model selection in neural networks, active learning, language  learning and evolutionary models of language change. \u003cbr\u003e  \u003cem\u003eThe Informational Complexity of Learning: Perspectives on Neural\u003c\/em\u003e  \u003cem\u003eNetworks and Generative Grammar\u003c\/em\u003e is a very interdisciplinary  work. Anyone interested in the interaction of computer science and  cognitive science should enjoy the book. Researchers in artificial  intelligence, neural networks, linguistics, theoretical computer  science, and statistics will find it particularly relevant.\u003c\/p\u003e \u003ch3\u003eDetails\u003c\/h3\u003e \u003cp\u003ePublished by: Springer\u003c\/p\u003e \u003cp\u003ePublication Date: 2012-10-16\u003c\/p\u003e \u003cp\u003eFormat: Paperback\u003c\/p\u003e \u003cp\u003e ISBN-10: 9781461374930\u003c\/p\u003e \u003cp\u003eISBN-13: 9781461374930\u003c\/p\u003e \u003cp\u003eDOI: 10.1007\/978-1-4615-5459-2\u003c\/p\u003e \u003cp\u003eDimensions: 235cm x155cm\u003c\/p\u003e \u003cp\u003ePages: 224\u003c\/p\u003e ","brand":"Springer","offers":[{"title":"Default Title","offer_id":44358760071308,"sku":"9781461374930","price":99.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0710\/9545\/1788\/files\/9781461374930.jpg?v=1755113545","url":"https:\/\/lateknightbooks.com\/products\/9781461374930","provider":"Late Knight Books and Services, LLC","version":"1.0","type":"link"}