| 书目名称 | The Informational Complexity of Learning | | 副标题 | Perspectives on Neur | | 编辑 | Partha Niyogi | | 视频video | | | 图书封面 |  | | 描述 | Among other topics, .The Informational Complexity ofLearning:. .Perspectives on Neural Networks and GenerativeGrammar. brings together two important but very different learningproblems within the same analytical framework. The first concerns theproblem of learning functional mappings using neural networks,followed by learning natural language grammars in the principles andparameters tradition of Chomsky. .These two learning problems are seemingly very different. Neuralnetworks are real-valued, infinite-dimensional, continuous mappings.On the other hand, grammars are boolean-valued, finite-dimensional,discrete (symbolic) mappings. Furthermore the research communitiesthat work in the two areas almost never overlap. .The book‘s objective is to bridge this gap. It uses the formaltechniques developed in statistical learning theory and theoreticalcomputer science over the last decade to analyze both kinds oflearning problems. By asking the same question - how muchinformation does it take to learn? - of both problems, ithighlights their similarities and differences. Specific resultsinclude model selection in neural networks, active learning, languagelearning and evolutionary models of lan | | 出版日期 | Book 1998 | | 关键词 | artificial intelligence; cognitive science; complexity; evolution; grammar; grammars; information; intellig | | 版次 | 1 | | doi | https://doi.org/10.1007/978-1-4615-5459-2 | | isbn_softcover | 978-1-4613-7493-0 | | isbn_ebook | 978-1-4615-5459-2 | | copyright | Springer Science+Business Media New York 1998 |
The information of publication is updating
|
|
发表于 2025-3-21 18:02:23
