Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/32464
Title: | Feature and Label Association Based on Granulation Entropy for Deep Neural Networks | Authors: | BELLO GARCIA, Marilyn NAPOLES RUIZ, Gonzalo Sánchez, Ricardo VANHOOF, Koen Bello, Rafael |
Issue Date: | 2020 | Publisher: | Springer, Cham | Source: | Lecture notes in computer science, 12179 , p. 225 -235 | Series/Report: | Lecture Notes in Artificial Intelligence | Series/Report no.: | 12179 | Abstract: | Pooling layers help reduce redundancy and the number of parameters before building a multilayered neural network that performs the remaining processing operations. Usually, pooling operators in deep learning models use an explicit topological organization, which is not always possible to obtain on multi-label data. In a previous paper, we proposed a pooling architecture based on association to deal with this issue. The association was defined by means of Pearson's correlation. However, features must exhibit a certain degree of correlation with each other, which might not hold in all situations. In this paper, we propose a new method that replaces the correlation measure with another one that computes the entropy in the information granules that are generated from two features or labels. Numerical simulations have shown that our proposal is superior in those datasets with low correlation. This means that it induces a significant reduction in the number of parameters of neural networks, without affecting their accuracy. | Keywords: | Granular computing;Rough sets;Association-based pooling;Deep learning;Multi-label classification | Document URI: | http://hdl.handle.net/1942/32464 | ISBN: | 978-3-030-52704-4 9783030527051 |
ISSN: | 0302-9743 | DOI: | 10.1007/978-3-030-52705-1_17 | ISI #: | 000713415600017 | Category: | C1 | Type: | Proceedings Paper | Validations: | ecoom 2022 vabb 2022 |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Bello2020_Chapter_FeatureAndLabelAssociationBase.pdf Restricted Access | Published version | 504.16 kB | Adobe PDF | View/Open Request a copy |
32464a.pdf | Peer-reviewed author version | 286 kB | Adobe PDF | View/Open |
Page view(s)
78
checked on Jun 9, 2022
Download(s)
10
checked on Jun 9, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.