CombPool layers

Last updated on Jan 24, 2023
More
Working example of a CombPool layer

This project implements CombPool layers, a new pooling layer that enables the linear combination of different pooling functions, generating increasing functions as a result. Implementation for the paper: Rodriguez-Martinez, I., Lafuente, J., Santiago, R. H., Dimuro, G. P., Herrera, F., & Bustince, H. (2022). Replacing pooling functions in Convolutional Neural Networks by linear combinations of increasing functions. Neural Networks, 152, 380-393..

Documentation is available in English and Spanish: https://github.com/iosurodri/CombPool

Deep Learning
Iosu Rodríguez Martínez
Iosu Rodríguez Martínez
PHD student on Artificial Intelligence

My research interests include Convolutional Neural Networks, aggregation theory and fuzzy logic.

Publications

Replacing pooling functions in Convolutional Neural Networks by linear combinations of increasing functions
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.
Iosu Rodríguez Martínez, Julio Lafuente, Santiago Regivan, Graçaliz Dimuro, Francisco Herrero, Humberto Bustince
Cite Project DOI