Title :
Back and counter propagation aberrations
Author_Institution :
Dept. of Electro-Optics, Houston Univ., Clear Lake, TX, USA
Abstract :
Variations on BPN (backward propagation network) and CPN (counter propagation networks) have been presented. The BPN variations are a little quicker and the CPN variations are a little more accurate. The author suggests that these variations should be tested on some other more difficult problems. To this end, a fault-tolerant (in software) handwriting recognizer is being developed using these BPN and CPN variations, along with an adaptive resonance network. Preliminary results indicate that by using the author´s equation with the BPN, a 20% decrease in learning time can be obtained, which represents a reduction from 30 to 24 hours for learning the alphabet.<>
Keywords :
artificial intelligence; character recognition; learning systems; neural nets; BPN; CPN; artificial intelligence; backward propagation network; character recognition; counter propagation aberrations; handwriting recognizer; machine learning; pattern recognition; Artificial intelligence; Character recognition; Learning systems; Neural networks;
Conference_Titel :
Neural Networks, 1988., IEEE International Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/ICNN.1988.23881