Share Email Print
cover

Proceedings Paper

Active learning of neural networks based on influential statistics
Author(s): Guillem Cuesta; Carlos Rio; Stanisław Jankowski
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

The paper presents a method of the training set selection in order to improve the generalization of neural networks. The data search is based on the estimation of their influence on the network expressed by the influential statistics. This active learning method is presented by using the didactic example. It can be concluded that the designed neural network for regression achieved high generalization score avoiding overfitting while trained on the minimal training set.

Paper Details

Date Published: 25 October 2013
PDF: 13 pages
Proc. SPIE 8903, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2013, 89032T (25 October 2013); doi: 10.1117/12.2035622
Show Author Affiliations
Guillem Cuesta, Univ. Ramon Llull (Spain)
Carlos Rio, Univ. Ramon Llull (Spain)
Stanisław Jankowski, Warsaw Univ. of Technology (Poland)


Published in SPIE Proceedings Vol. 8903:
Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2013
Ryszard S. Romaniuk, Editor(s)

© SPIE. Terms of Use
Back to Top