Proceedings of the KSRS Conference (대한원격탐사학회:학술대회논문집)
- 2003.11a
- /
- Pages.429-431
- /
- 2003
- /
- 1226-9743(pISSN)
An Efficient and Accurate Artificial Neural Network through Induced Learning Retardation and Pruning Training Methods Sequence
- Bandibas, Joel (Geological Survey of Japan, AIST) ;
- Kohyama, Kazunori (National Institute of Livestock and Grassland Science) ;
- Wakita, Koji (Geological Survey of Japan, AIST)
- Published : 2003.11.03
Abstract
The induced learning retardation method involves the temporary inhibition of the artificial neural network’s active units from participating in the error reduction process during training. This stimulates the less active units to contribute significantly to reduce the network error. However, some less active units are not sensitive to stimulation making them almost useless. The network can then be pruned by removing the less active units to make it smaller and more efficient. This study focuses on making the network more efficient and accurate by developing the induced learning retardation and pruning sequence training method. The developed procedure results to faster learning and more accurate artificial neural network for satellite image classification.