Massively Parallel Artificial Intelligence

Front Cover
Hiroaki Kitano, James A. Hendler
AAAI Press, 1994 - Computers - 426 pages
0 Reviews

The increased sophistication and availability of massively parallel supercomputershas had two major impacts on research in artificial intelligence, both of which are addressed inthis collection of exciting new AI theories and experiments. Massively parallel computers have beenused to push forward research in traditional AI topics such as vision, search, and speech. Moreimportant, these machines allow AI to expand in exciting new ways by taking advantage of research inneuroscience and developing new models and paradigms, among them associate memory, neural networks,genetic algorithms, artificial life, society-of-mind models, and subsumption architectures.A numberof chapters show that massively parallel computing enables AI researchers to handle significantlylarger amounts of data in real time, which changes the way that AI systems can be built, which inturn makes memory-based reasoning and neural-network-based vision systems become practical. Otherchapters present the contrasting view that massively parallel computing provides a platform to modeland build intelligent systems by simulating the (massively parallel) processes that occur innature.

From inside the book

What people are saying - Write a review

We haven't found any reviews in the usual places.

Contents

Massively Parallel Matching of Knowledge Structures
59
Selecting Salient Features for Machine Learning from
103
A Parallel Computational Model for Integrated Speech
139
Copyright

6 other sections not shown

Common terms and phrases

References to this book

All Book Search results »

About the author (1994)

James Hendler is Director of Semantic Web and Agent Technology, Maryland Information and Network Dynamics Laboratory, University of Maryland.

Bibliographic information