Speed Up of the SAMANN Neural Network Retraining
Sammon’s mapping is a well-known procedure for mapping data from a higher-dimensional space onto a lower-dimensional one. The original algorithm has a disadvantage. It lacks generalization, which means that new points cannot be added to the obtained map without recalculating it. SAMANN neural network, that realizes Sammon’s algorithm, provides a generalization capability of projecting new data. Speed up of the SAMANN network retraining when the new data points appear has been analyzed in this paper. Two strategies for retraining the neural network that realizes the multidimensional data visualization have been proposed and then the analysis has been made.
KeywordsNeural Network Projection Error Primary Dataset Iris Dataset Nonlinear Projection
Unable to display preview. Download preview PDF.
- 3.Jain, A.K., Mao, J.: Artificial neural network for nonlinear projection of multivariate data. In: Proc. IEEE International Joint Conference Neural Network, vol. 3, pp. 335–340 (1992)Google Scholar
- 5.Medvedev, V., Dzemyda, G.: Optimization of the local search in the training for SAMANN neural network. Journal of Global Optimization (to appear)Google Scholar
- 9.Fisher, R.A.: The use of multiple measurements in taxonomic problem. Annual Eugenics 7, Part II, 179–188 (1936)Google Scholar
- 10.Australian Credit Approval, http://www.niaad.liacc.up.pt/old/statlog/datasets/australian/australian.doc.html