The Informational Complexity of Learning: Perspectives on Neural Networks and Generative Grammar (Paperback)Partha Niyogi (author)
- We can order this
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.
Publisher: Springer-Verlag New York Inc.
Number of pages: 224
Weight: 391 g
Dimensions: 235 x 155 x 13 mm
Edition: Softcover reprint of the original 1st ed. 199
You may also be interested in...
Please sign in to write a review