HIERtalker: A default hierarchy of high order neural networks that learns to read English aloud

Conference · Fri Jan 01 00:00:00 EST 1988

OSTI ID:6851611

An, Z G; Mniszewski, S M; Lee, Y C; Papcun, G; Doolen, G D

A new learning algorithm based on a default hierarchy of high order neural networks has been developed that is able to generalize as well as handle exceptions. It learns the ''building blocks'' or clusters of symbols in a stream that appear repeatedly and convey certain messages. The default hierarchy prevents a combinatoric explosion of rules. A simulator of such a hierarchy, HIERtalker, has been applied to the conversion of English words to phonemes. Achieved accuracy is 99% for trained words and ranges from 76% to 96% for sets of new words. 8 refs., 4 figs., 1 tab.

• Research Organization: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)
• DOE Contract Number: W-7405-ENG-36
• OSTI ID: 6851611
• Report Number(s): LA-UR-88-1849; CONF-880745-5; ON: DE88014455
• Resource Relation: Conference: IEEE annual international conference on neural networks, San Diego, CA, USA, 24 Jul 1988; Other Information: Portions of this document are illegible in microfiche products
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
SPEECH SYNTHESIZERS
ALGORITHMS
COMPUTER ARCHITECTURE
EFFICIENCY
LEARNING
PERFORMANCE
ELECTRONIC EQUIPMENT
EQUIPMENT
MATHEMATICAL LOGIC
990220* - Computers
Computerized Models
& Computer Programs- (1987-1989)