Title :
Phenomenons and Methods: Uncertainty in Internal Symmetry Nets with Backpropagation in Image Processing
Author_Institution :
Sch. of Comput. Sci. & Eng., Univ. of New South Wales, Sydney, NSW, Australia
Abstract :
Internal symmetry nets are a new developed class of cellular neural networks. It originated from internal symmetry quantum physics, and noted by five irreducible representations from group theory. In this paper, uncertainty of the nets in a series of image processing tasks will be analyzed and the methods to deal with problems will be showed after each step of analysis.
Keywords :
backpropagation; group theory; image processing; backpropagation; group theory; image processing; internal symmetry nets; internal symmetry quantum physics; Backpropagation; Cellular neural networks; Equations; Image analysis; Image processing; Image segmentation; Intelligent networks; Lattices; Physics; Uncertainty; back propagation; internal symmetry; momentum and learning rate; overfitting; recurrent cycles;
Conference_Titel :
Intelligent Ubiquitous Computing and Education, 2009 International Symposium on
Conference_Location :
Chengdu
Print_ISBN :
978-0-7695-3619-4
DOI :
10.1109/IUCE.2009.133
