Translator Disclaimer
Paper
25 October 2013 Active learning of neural networks based on influential statistics
Author Affiliations +
Proceedings Volume 8903, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2013; 89032T (2013) https://doi.org/10.1117/12.2035622
Event: Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2013, 2013, Wilga, Poland
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.
© (2013) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Guillem Cuesta, Carlos Rio, and Stanisław Jankowski "Active learning of neural networks based on influential statistics", Proc. SPIE 8903, Photonics Applications in Astronomy, Communications, Industry, and High-Energy Physics Experiments 2013, 89032T (25 October 2013); https://doi.org/10.1117/12.2035622
PROCEEDINGS
13 PAGES


SHARE
Advertisement
Advertisement
Back to Top