Title :
Force learn algorithm-training a neural net with patterns which have highest errors
Abstract :
Describes training methods of neural nets with the backpropagation learning algorithm in which priority is given to the patterns of the training set with the maximum error during the training
Keywords :
backpropagation; neural nets; backpropagation learning algorithm; force learn algorithm; maximum error; training methods; Backpropagation algorithms; Error correction; Intelligent networks; Neural networks; Pattern recognition; Shape;
Conference_Titel :
Neural Network Applications in Electrical Engineering, 2000. NEUREL 2000. Proceedings of the 5th Seminar on
Conference_Location :
Belgrade
Print_ISBN :
0-7803-5512-1
DOI :
10.1109/NEUREL.2000.902382
