DocumentCode
3335199
Title
HNETTER-a heuristically driven neural reasoning system
Author
Kaplan, Dmitry ; Johnson, David L.
Author_Institution
Washington Univ., Seattle, WA, USA
fYear
1988
fDate
24-27 July 1988
Firstpage
507
Abstract
A description is given of a probabilistic reasoning system that attains understanding of simple 2D shapes and their properties from a small number of possibly incorrect examples. The system represents a fusion of heuristic reasoning and artificial neural nets with the former accomplishing generation and pruning of hypotheses and the latter assimilating the arbitrarily complex combinations of relevant hypotheses. The authors discuss the relative advantages of both approaches and suggest how, based on their experience, a learning task can be successfully split between them.<>
Keywords
computerised pattern recognition; computerised picture processing; heuristic programming; learning systems; neural nets; probabilistic logic; 2D shapes; HNETTER; complex combinations; heuristically driven neural reasoning system; hypothesis combination pruning; hypothesis generation; hypothesis pruning; learning system; pattern recognition; picture processing; probabilistic reasoning system; shape recognition; Image processing; Learning systems; Neural networks; Pattern recognition; Stochastic logic;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 1988., IEEE International Conference on
Conference_Location
San Diego, CA, USA
Type
conf
DOI
10.1109/ICNN.1988.23966
Filename
23966
Link To Document