Title |
Vizualizavimui skirto neuroninio tinklo mokymosi greičio optimizavimas / |
Translation of Title |
Optimization of the learning rate in the algorithm for data visualization. |
Authors |
Medvedev, Viktor ; Dzemyda, Gintautas |
DOI |
10.15388/LMR.2005.29205 |
Full Text |
|
Is Part of |
Lietuvos matematikos rinkinys. 2005, T. 45, spec, Nr, p. 426-431.. ISSN 0132-2818 |
Keywords [eng] |
Data, multidimensional ; Visualization ; Mapping, Sammon's ; Network, SAMANN ; Learning rate |
Abstract [eng] |
In this paper, we discuss the visualization of multidimensional data. A well-known procedure for mapping data from a high-dimensional space onto a lower-dimensional one is Sammon's mapping. The paper describes an unsupervised backpropagation algorithm to train a multilayer feed-forward neural network (SAMANN) to perform the Sammon's nonlinear projection. In our research the emphasis is put on the optimization of the learning rate to save computation time without losing the mapping quality. |
Type |
Journal article |
Language |
Lithuanian |
Publication date |
2005 |
CC license |
|