Title :
Robust learning in adaptive processing of data structures for tree representation based image classification
Author :
Cho, Siu-Yeung ; Chi, Zheru ; Wang, Zhiyong ; Siu, Wan-chi
Author_Institution :
Centre for Multimedia Signal Process., Hong Kong Polytech. Univ., Kowloon, China
Abstract :
In this paper, 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 gradient information can be recovered to overcome the learning long-term dependency problem for this adaptive processing.
Keywords :
adaptive signal processing; backpropagation; image classification; least squares approximations; natural scenes; neural nets; quadtrees; backpropagation through structure algorithm; data structure adaptive processing; free parameter optimization; layer-by-layer least squares method; learning scheme; live plant images; natural scene images; node representation; quad-tree structure; robust learning; single-hidden-layer neural network; tree representation based image classification; vanishing gradient information; Adaptive signal processing; Backpropagation algorithms; Convergence; Data structures; Image classification; Neural networks; Pixel; Robustness; Tree data structures; Tree graphs;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1048249
