Low-Rank Deep Convolutional Neural Network for Multitask Learning
Joint Authors
Su, Fang
Shang, Hai-Yang
Wang, Jing-Yan
Source
Computational Intelligence and Neuroscience
Issue
Vol. 2019, Issue 2019 (31 Dec. 2019), pp.1-10, 10 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2019-05-20
Country of Publication
Egypt
No. of Pages
10
Main Subjects
Abstract EN
In this paper, we propose a novel multitask learning method based on the deep convolutional network.
The proposed deep network has four convolutional layers, three max-pooling layers, and two parallel fully connected layers.
To adjust the deep network to multitask learning problem, we propose to learn a low-rank deep network so that the relation among different tasks can be explored.
We proposed to minimize the number of independent parameter rows of one fully connected layer to explore the relations among different tasks, which is measured by the nuclear norm of the parameter of one fully connected layer, and seek a low-rank parameter matrix.
Meanwhile, we also propose to regularize another fully connected layer by sparsity penalty so that the useful features learned by the lower layers can be selected.
The learning problem is solved by an iterative algorithm based on gradient descent and back-propagation algorithms.
The proposed algorithm is evaluated over benchmark datasets of multiple face attribute prediction, multitask natural language processing, and joint economics index predictions.
The evaluation results show the advantage of the low-rank deep CNN model over multitask problems.
American Psychological Association (APA)
Su, Fang& Shang, Hai-Yang& Wang, Jing-Yan. 2019. Low-Rank Deep Convolutional Neural Network for Multitask Learning. Computational Intelligence and Neuroscience،Vol. 2019, no. 2019, pp.1-10.
https://search.emarefa.net/detail/BIM-1129570
Modern Language Association (MLA)
Su, Fang…[et al.]. Low-Rank Deep Convolutional Neural Network for Multitask Learning. Computational Intelligence and Neuroscience No. 2019 (2019), pp.1-10.
https://search.emarefa.net/detail/BIM-1129570
American Medical Association (AMA)
Su, Fang& Shang, Hai-Yang& Wang, Jing-Yan. Low-Rank Deep Convolutional Neural Network for Multitask Learning. Computational Intelligence and Neuroscience. 2019. Vol. 2019, no. 2019, pp.1-10.
https://search.emarefa.net/detail/BIM-1129570
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1129570