Among other topics, The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar 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.
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.
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.
The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar 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.
"synopsis" may belong to another edition of this title.
Seller: Lucky's Textbooks, Dallas, TX, U.S.A.
Condition: New. Seller Inventory # ABLIING23Feb2416190185007
Quantity: Over 20 available
Seller: Grand Eagle Retail, Mason, OH, U.S.A.
Hardcover. Condition: new. Hardcover. Among other topics, this work brings together two 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. 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. 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. The book is an 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 should find it particularly relevant. Among other topics, The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar brings together two important but very different learning problems within the same analytical framework. Shipping may be from multiple locations in the US or from the UK, depending on stock availability. Seller Inventory # 9780792380818
Quantity: 1 available
Seller: Ria Christie Collections, Uxbridge, United Kingdom
Condition: New. In English. Seller Inventory # ria9780792380818_new
Quantity: Over 20 available
Seller: Books Puddle, New York, NY, U.S.A.
Condition: New. pp. 252. Seller Inventory # 263104613
Quantity: 4 available
Seller: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Germany
Buch. Condition: Neu. This item is printed on demand - it takes 3-4 days longer - Neuware -Among other topics, The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar 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. 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. 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. The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar 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. 248 pp. Englisch. Seller Inventory # 9780792380818
Quantity: 2 available
Seller: Majestic Books, Hounslow, United Kingdom
Condition: New. Print on Demand pp. 252 52:B&W 6.14 x 9.21in or 234 x 156mm (Royal 8vo) Case Laminate on White w/Gloss Lam. Seller Inventory # 5824698
Quantity: 4 available
Seller: moluna, Greven, Germany
Gebunden. Condition: New. Dieser Artikel ist ein Print on Demand Artikel und wird nach Ihrer Bestellung fuer Sie gedruckt. Among other topics, The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar brings together two important but very different learning problems within the same analytical framework. The first conc. Seller Inventory # 5970659
Quantity: Over 20 available
Seller: Biblios, Frankfurt am main, HESSE, Germany
Condition: New. PRINT ON DEMAND pp. 252. Seller Inventory # 183104623
Quantity: 4 available
Seller: THE SAINT BOOKSTORE, Southport, United Kingdom
Hardback. Condition: New. This item is printed on demand. New copy - Usually dispatched within 5-9 working days 1210. Seller Inventory # C9780792380818
Quantity: Over 20 available
Seller: buchversandmimpf2000, Emtmannsberg, BAYE, Germany
Buch. Condition: Neu. Neuware -Among other topics, The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar 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.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.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.The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar 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.Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg 252 pp. Englisch. Seller Inventory # 9780792380818
Quantity: 2 available