Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/32436
Title: | Deep neural network to extract high-level features and labels in multi-label classification problems | Authors: | BELLO GARCIA, Marilyn NAPOLES RUIZ, Gonzalo Sánchez, Ricardo Bello, Rafael VANHOOF, Koen |
Issue Date: | 2020 | Publisher: | ELSEVIER | Source: | Neurocomputing (Amsterdam), 413 , p. 259 -270 | Abstract: | Pooling layers help reduce redundancy and the number of parameters in deep neural networks without the need of performing additional learning processes. Although these operators are able to deal with both single-label and multi-label problems they are specifically aimed at reducing feature space. However, in the case of multi-label data, this should also be done in the label space. On the other hand, in spite of their success, existing pooling operators are not ideal when handling (multi-label) datasets that do not have an explicit topological organization. In this paper, we present a deep neural architecture using bidirectional association-based pooling layers to extract high-level features and labels in multi-label classification problems. Our approach uses an association function to detect distinct pairs of neurons that will be aggregated into pooled neurons. In the first pooling layer, our proposal computes the Pearson correlation among the variables as the basis to quantify the association values. In addition, we propose an iterative procedure that allows estimating the association degree among pooled neurons in deeper layers without the need of recomputing the correlation matrix. The main advantage of this deep neural architecture is that it allows extracting high-level features and labels on datasets with no specific topological organization. The numerical results show that our bidirectional neural network helps reduce the number of problem features and labels while preserving network's discriminatory power. | Keywords: | deep neural networks;multi-label classification;high-level features;high-level labels;association-based pooling | Document URI: | http://hdl.handle.net/1942/32436 | ISSN: | 0925-2312 | e-ISSN: | 1872-8286 | DOI: | 10.1016/j.neucom.2020.06.117 | ISI #: | WOS:000579803700022 | Rights: | 2020 Elsevier B.V. All rights reserved | Category: | A1 | Type: | Journal Contribution | Validations: | ecoom 2021 |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
manuscript.pdf | Peer-reviewed author version | 687.79 kB | Adobe PDF | View/Open |
1-s2.0-S0925231220311115-main.pdf Restricted Access | Published version | 1.05 MB | Adobe PDF | View/Open Request a copy |
WEB OF SCIENCETM
Citations
23
checked on Oct 14, 2024
Page view(s)
70
checked on Sep 6, 2022
Download(s)
46
checked on Sep 6, 2022
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.