Title :
Selection of training samples for learning with hints
Author :
Lampinen, Jouko ; Litkey, Paula ; Hakkarainen, Harri
Author_Institution :
Lab. of Comput. Eng., Helsinki Univ. of Technol., Espoo, Finland
Abstract :
Training with hints is a powerful method for incorporating almost any type of prior knowledge into neural network models. In this paper we demonstrate how the hints can be constructed from numerical approximation of the regularization cost function, and discuss the problem of selecting the hint samples. We give a simple algorithm for placing the hint samples in such regions in the input space where the hint error is large, and for selecting the minimum sufficient set of hint samples by removing the correlated samples
Keywords :
approximation theory; learning (artificial intelligence); neural nets; optimisation; approximation; cost function; learning with hints; minimisation; neural network; sample selection; Computer networks; Cost function; Fuzzy sets; Knowledge engineering; Laboratories; Neural networks; Nonlinear distortion; Power engineering and energy; Power engineering computing; Testing;
Conference_Titel :
Neural Networks, 1999. IJCNN '99. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-5529-6
DOI :
10.1109/IJCNN.1999.831176
