Title :
A self-learning threshold-controlled neural network
Author :
Hartstein, A. ; Koch, R.H.
Author_Institution :
IBM Thomas J. Watson Res. Center, Yorktown Heights, NY, USA
Abstract :
A neural network structure is proposed that is controlled by device thresholds rather than multiplicative factors. This network has the feature that the learning parameter is embodied locally in the device thresholds. The network is shown to be capable of learning by example, as well as exhibiting other desirable features of the Hopfield type networks.<>
Keywords :
artificial intelligence; learning systems; neural nets; Hopfield type networks; artificial intelligence; learning parameter; neural network structure; self learning threshold control; Artificial intelligence; Learning systems; Neural networks;
Conference_Titel :
Neural Networks, 1988., IEEE International Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/ICNN.1988.23875
