Active learning of neural networks based on influential statistics

Guillem Cuesta; Carlos Rio; Stanisław Jankowski

doi:10.1117/12.2035622

25 October 2013 Active learning of neural networks based on influential statistics

Guillem Cuesta, Carlos Rio, Stanisław Jankowski

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.

Citation Download Citation

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

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available