Person:
Rodríguez Martínez, Iosu

Profile Picture

Email Address

person.page.identifierURI

https://academica-e.unavarra.es/handle/2454/49879

Birth Date

Research Projects

Organizational Units

Job Title

Last Name

Rodríguez Martínez

First Name

Iosu

person.page.departamento

Estadística, Informática y Matemáticas

person.page.instituteName

ORCID

0000-0002-9960-0203

person.page.upna

811655

Name

Filters

20221
Reset filters

Settings

Author: Lafuente López, Julio × Subject: Convolutional Neural Networks ×

Search Results

Now showing 1 - 1 of 1
  • Thumbnail Image
    PublicationOpen Access
    Replacing pooling functions in convolutional neural networks by linear combinations of increasing functions
    (Elsevier, 2022) Rodríguez Martínez, Iosu; Lafuente López, Julio; Santiago, Regivan; Pereira Dimuro, Graçaliz; Herrera, Francisco; Bustince Sola, Humberto; Estadística, Informática y Matemáticas; Estatistika, Informatika eta Matematika; Gobierno de Navarra / Nafarroako Gobernua
    Traditionally, Convolutional Neural Networks make use of the maximum or arithmetic mean in order to reduce the features extracted by convolutional layers in a downsampling process known as pooling. However, there is no strong argument to settle upon one of the two functions and, in practice, this selection turns to be problem dependent. Further, both of these options ignore possible dependencies among the data. We believe that a combination of both of these functions, as well as of additional ones which may retain different information, can benefit the feature extraction process. In this work, we replace traditional pooling by several alternative functions. In particular, we consider linear combinations of order statistics and generalizations of the Sugeno integral, extending the latter¿s domain to the whole real line and setting the theoretical base for their application. We present an alternative pooling layer based on this strategy which we name ¿CombPool¿ layer. We replace the pooling layers of three different architectures of increasing complexity by CombPool layers, and empirically prove over multiple datasets that linear combinations outperform traditional pooling functions in most cases. Further, combinations with either the Sugeno integral or one of its generalizations usually yield the best results, proving a strong candidate to apply in most architectures.