16th International Conference on Pattern Recognition (ICPR'02) - Volume 2
Robust Learning in Adaptive Processing of Data Structures for Tree Representation Based Image Classification
Quebec City, QC, Canada
August 11-August 15
ISBN: 0-7695-1695-X
In this paper, a novel robust learning in adaptive processing of data structures for tree representation based image classification is proposed. The idea of this learning scheme is to optimize the free parameters of the node representation in data structures by using the layer-by-layer least squares method. The vanishing of gradient information can be recovered to overcome in learning long-term dependency problem for this adaptive processing.
Citation:
Siu-Yeung Cho, Zheru Chi, Zhiyong Wang, Wan-Chi Siu, "Robust Learning in Adaptive Processing of Data Structures for Tree Representation Based Image Classification," icpr, vol. 2, pp.20108, 16th International Conference on Pattern Recognition (ICPR'02) - Volume 2, 2002