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.
|Number of pages||4|
|Journal||Proceedings - International Conference on Pattern Recognition|
|Publication status||Published - 1 Dec 2002|
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition