|
Digital Library of the
European Council for Modelling and Simulation |
Title: |
Reducing Overconfidence In Neural Networks By Dynamic Variation of
Recognizer Relevance |
Authors: |
Konstantin B. Bulatov, Dmitry V.
Polevoy |
Published in: |
(2015).ECMS 2015 Proceedings edited
by: Valeri M. Mladenov, Grisha Spasov, Petia Georgieva, Galidiya Petrova, European
Council for Modeling and Simulation. doi:10.7148/2015 ISBN:
978-0-9932440-0-1 29th
European Conference on Modelling and Simulation, Albena (Varna), Bulgaria,
May 26th – 29th, 2015 |
Citation
format: |
Konstantin
B. Bulatov, Dmitry V. Polevoy
(2015). Reducing Overconfidence In Neural Networks
By Dynamic Variation of Recognizer Relevance, ECMS 2015 Proceedings edited
by: Valeri M. Mladenov, Petia Georgieva, Grisha Spasov, Galidiya Petrova European Council for Modeling and Simulation. doi:10.7148/2015-0488 |
DOI: |
http://dx.doi.org/10.7148/2015-0488 |
Abstract: |
Contemporary recognition systems use
various methods of symbol recognition and post-processing methods designed
for enhancing the quality of text recognition. For some recognition problems
it may be difficult to create an adequate dataset for training symbol recognizers,
so several symbol recognizers are used to ensure better performance. In this
paper the concept of recognizer relevance is introduced as a way of analysing the recognizer output. A method is described
using this concept, allowing to use external
information about the input samples in order to balance the contributions of the
recognizer and the post-processing subsystem. |
Full
text: |