Replacing pooling functions in convolutional neural networks by linear combinations of increasing functions
| Autor: | Iosu Rodriguez-Martinez, Julio Lafuente, Regivan H.N. Santiago, Graçaliz Pereira Dimuro, Francisco Herrera, Humberto Bustince |
|---|---|
| Přispěvatelé: | Universidad Pública de Navarra. Departamento de Estadística, Informática y Matemáticas, Nafarroako Unibertsitate Publikoa. Estatistika, Informatika eta Matematikak Saila, Gobierno de Navarra / Nafarroako Gobernua, Universidad Pública de Navarra. Departamento de Universidad Pública de Navarra. Departamento de Estadística, Informática y Matemáticas, Nafarroako Unibertsitate Publikoa. Nafarroako Unibertsitate Publikoa. Estatistika, Informatika eta Matematikak Saila Saila |
| Rok vydání: | 2022 |
| Předmět: | |
| Zdroj: | Academica-e. Repositorio Institucional de la Universidad Pública de Navarra instname Digibug. Repositorio Institucional de la Universidad de Granada |
| Popis: | 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. Tracasa Instrumental (iTRACASA), Spain Gobierno de Navarra-Departamento de Universidad, Innovacion y Transformacion Digital, Spain Spanish Ministry of Science, Spain PID2019-108392GB-I00 Andalusian Excellence project, Spain PID2019-108392GB-I00 Conselho Nacional de Desenvolvimento Cientifico e Tecnologico (CNPQ) PC095-096 Fundacao de Amparo a Ciencia e Tecnologia do Estado do Rio Grande do Sul (FAPERGS) P18-FR-4961 301618/2019-4 19/2551-000 1279-9 |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|