Long-term Cognitive Network-based architecture for multi-label classification
Nápoles,Gonzalo Bello,Marilyn Salgueiro,Yamisleydi
Nápoles,Gonzalo
Bello,Marilyn
Salgueiro,Yamisleydi
Abstract
This paper presents a neural system to deal with multi-label classification problems that might involve sparse features. The architecture of this model involves three sequential blocks with well-defined functions. The first block consists of a multilayered feed-forward structure that extracts hidden features, thus reducing the problem dimensionality. This block is useful when dealing with sparse problems. The second block consists of a Long-term Cognitive Network-based model that operates on features extracted by the first block. The activation rule of this recurrent neural network is modified to prevent the vanishing of the input signal during the recurrent inference process. The modified activation rule combines the neurons’ state in the previous abstract layer (iteration) with the initial state. Moreover, we add a bias component to shift the transfer functions as needed to obtain good approximations. Finally, the third block consists of an output layer that adapts the second block’s outputs to the label space. We propose a backpropagation learning algorithm that uses a squared hinge loss function to maximize the margins between labels to train this network. The results show that our model outperforms the state-of-the-art algorithms in most datasets.
Description
Funding Information: The authors would like to sincerely thank Isel Grau from the Vrije Universiteit Brussel, Belgium, who pointed out the advantages of using the squared hinge function instead of the mean squared error. This paper was partially supported by the Program CONICYT FONDECYT de Postdoctorado, Chile through the project 3200284 . Publisher Copyright: © 2021 The Author(s)
Date
2021-08
Journal Title
Journal ISSN
Volume Title
Publisher
Research Projects
Organizational Units
Journal Issue
Keywords
Long-term cognitive networks, Recurrent neural networks, Backpropagation, Multi-label classification
Citation
Nápoles, G, Bello, M & Salgueiro, Y 2021, 'Long-term Cognitive Network-based architecture for multi-label classification', Neural Networks: The official journal of the International Neural Network Society, European Neural Network Society, Japanese Neural Network Society, vol. 140, pp. 39-48. https://doi.org/10.1016/j.neunet.2021.03.001