Error-correcting output codes in the framework of deep ordinal classification

Áreas de investigación:

• Applications - Health
• Methodology - Machine learning
• Methodology - Ordinal classification
• Methodology - Convolutional Neural Networks

Año:

2021

Tipo de publicación:

Artículo en conferencia

Palabras clave:

Artificial Neural Networks, Ordinal Classification

Autores:

• Barbero-Gómez, Javier
• Gutiérrez, Pedro Antonio
• Hervás-Martínez, César

Volumen:

12862

Título del libro:

2021 International Work-conference on Artificial Neural Networks (IWANN 2021)

Número:

Part II

Serie:

Lecture Notes in Computer Science (LNCS)

Páginas:

3-13

Organización:

Online

Mes:

16nd-18th June

ISBN:

978-3-030-85029-6

ISSN:

0302-9743

BibTex:

@conference{BarberoECOCOrdinalIWANN, author = "Javier Barbero-G{\'o}mez and Pedro Antonio Guti{\'e}rrez and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "Automatic classification tasks have been revolutionized by Convolutional Neural Networks (CNNs), but the focus has been on binary and nominal classification tasks. Only recently, ordinal classification (where class labels present a natural ordering) has been tackled through the framework of CNNs, such as adapting the classic Proportional Odds Model to deep architectures. Also, ordinal classification datasets commonly present a high imbalance in the number of samples of each class, making it an even harder problem. In this work, we present a new CNN architecture based on the Ordinal Binary Decomposition (OBD) technique using Error-Correcting Output Codes (ECOC) and show how it can improve performance over previously proposed methods.", booktitle = "2021 International Work-conference on Artificial Neural Networks (IWANN 2021)", doi = "10.1007/978-3-030-85099-9_1", isbn = "978-3-030-85029-6", issn = "0302-9743", keywords = "Artificial Neural Networks, Ordinal Classification", month = "16nd-18th June", number = "Part II", organization = "Online", pages = "3-13", publisher = "Springer", series = " Lecture Notes in Computer Science (LNCS)", title = "{E}rror-correcting output codes in the framework of deep ordinal classification", url = "doi.org/10.1007/978-3-030-85099-9_1", volume = "12862", year = "2021", }

Abstract:

Automatic classification tasks have been revolutionized by Convolutional Neural Networks (CNNs), but the focus has been on binary and nominal classification tasks. Only recently, ordinal classification (where class labels present a natural ordering) has been tackled through the framework of CNNs, such as adapting the classic Proportional Odds Model to deep architectures. Also, ordinal classification datasets commonly present a high imbalance in the number of samples of each class, making it an even harder problem. In this work, we present a new CNN architecture based on the Ordinal Binary Decomposition (OBD) technique using Error-Correcting Output Codes (ECOC) and show how it can improve performance over previously proposed methods.