Fast training algorithms for large data sets with application to classification of multispectral images
Date of Original Version
Two methods of classification and related fast training algorithms are compared with each other and with backpropagation in this paper. The first method is the Discriminant Neural Network (DNN) [1, 2]. One hidden node is added at each design stage until the DNN meets the design requirements. The second method uses the Radial Basis Function Network (RBF) . We modify the RBF by solving a succession of binary classification problems in order to provide fast training. These two classification methods are applied to automatically classify 14 categories of land cover using multispectral aerial images. We find that the training times for the DNN and the modified RBF (MRBF) are much less than the training times for backpropagation or RBF. The performances of DNN (72%) and MRBF (60%) are better than obtained by linear discriminant analysis (LDA) (55%) . The resulting structure and computations are simpler for the DNN than for the other methods.
Publication Title, e.g., Journal
Conference Record - Asilomar Conference on Signals, Systems and Computers
Li, Qi, Donald W. Tufts, Roland J. Duhaime, and Peter V. August. "Fast training algorithms for large data sets with application to classification of multispectral images." Conference Record - Asilomar Conference on Signals, Systems and Computers 2, (1994). doi: 10.1109/ACSSC.1994.471680.