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.
US$ 2.64 shipping within U.S.A.
Destination, rates & speedsSeller: Best Price, Torrance, CA, U.S.A.
Condition: New. SUPER FAST SHIPPING. Seller Inventory # 9781461374930
Quantity: 2 available
Seller: Grand Eagle Retail, Mason, OH, U.S.A.
Paperback. Condition: new. Paperback. 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. 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 # 9781461374930
Quantity: 1 available
Seller: Lucky's Textbooks, Dallas, TX, U.S.A.
Condition: New. Seller Inventory # ABLIING23Mar2716030033949
Quantity: Over 20 available
Seller: GreatBookPrices, Columbia, MD, U.S.A.
Condition: New. Seller Inventory # 19494824-n
Quantity: 15 available
Seller: Ria Christie Collections, Uxbridge, United Kingdom
Condition: New. In. Seller Inventory # ria9781461374930_new
Quantity: Over 20 available
Seller: GreatBookPrices, Columbia, MD, U.S.A.
Condition: As New. Unread book in perfect condition. Seller Inventory # 19494824
Quantity: 15 available
Seller: BuchWeltWeit Ludwig Meier e.K., Bergisch Gladbach, Germany
Taschenbuch. 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. 252 pp. Englisch. Seller Inventory # 9781461374930
Quantity: 2 available
Seller: Books Puddle, New York, NY, U.S.A.
Condition: New. pp. 252. Seller Inventory # 2654513275
Quantity: 4 available
Seller: moluna, Greven, Germany
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 # 4195626
Quantity: Over 20 available
Seller: Majestic Books, Hounslow, United Kingdom
Condition: New. Print on Demand pp. 252 49:B&W 6.14 x 9.21 in or 234 x 156 mm (Royal 8vo) Perfect Bound on White w/Gloss Lam. Seller Inventory # 55079332
Quantity: 4 available