Title :
Speeding up artificial neural networks in the ´real´ world
Author_Institution :
MCC, Austin, TX, USA
Abstract :
Summary form only given, as follows. A novel heuristic, called focused-attention backpropagation (FAB) learning, is introduced. FAB enhances the backpropagation procedure by focusing attention on the exemplar patterns that are most difficult to learn. Results are reported using FAB learning to train multilayer feedforward artificial neural networks to represent real-valued elementary functions. The rate of learning observed for FAB is 1.5 to 10 times faster than for backpropagation.<>
Keywords :
learning systems; neural nets; focused-attention backpropagation; heuristic; learning systems; multilayer feedforward networks; neural networks; Learning systems; Neural networks;
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
DOI :
10.1109/IJCNN.1989.118520
