Document Type
Conference Proceeding
Publication Date
7-2003
Subjects
Neural networks -- Structure, Pattern recognition, Fourier transformations, Reconstructability Analysis, Information Theory, Probabilistic graphical modeling, Multivariate analysis discrete multivariate modeling, Data mining
Abstract
We demonstrate the use of Reconstructability Analysis to reduce the number of input variables for a neural network. Using the heart disease dataset we reduce the number of independent variables from 13 to two, while providing results that are statistically indistinguishable from those of NNs using the full variable set. We also demonstrate that rule lookup tables obtained directly from the data for the RA models are almost as effective as NNs trained on model variables.
Rights
This is the author's manuscript version. The final version is available from the publisher: https://ieeexplore.ieee.org/document/1224053
DOI
10.1109/IJCNN.2003.1224053
Persistent Identifier
https://archives.pdx.edu/ds/psu/32430
Citation Details
S. Shervais and M. Zwick, "Using reconstructability analysis to select input variables for artificial neural networks," Proceedings of the International Joint Conference on Neural Networks, 2003., Portland, OR, 2003, pp. 3022-3026 vol.4.
Description
Presented at the International Joint Conference on Neural Nets, Portland OR, July 20-24, 2003.