Feature and Label Association Based on Granulation Entropy for Deep Neural Networks

Marilyn Bello, Gonzalo Nápoles, Ricardo Sánchez, Koen Vanhoof, Rafael Bello

    Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

    Abstract

    Pooling layers help reduce redundancy and the number of parameters before building a multilayered neural network that performs the remaining processing operations. Usually, pooling operators in deep learning models use an explicit topological organization, which is not always possible to obtain on multi-label data. In a previous paper, we proposed a pooling architecture based on association to deal with this issue. The association was defined by means of Pearson's correlation. However, features must exhibit a certain degree of correlation with each other, which might not hold in all situations. In this paper, we propose a new method that replaces the correlation measure with another one that computes the entropy in the information granules that are generated from two features or labels. Numerical simulations have shown that our proposal is superior in those datasets with low correlation. This means that it induces a significant reduction in the number of parameters of neural networks, without affecting their accuracy.
    Original languageEnglish
    Title of host publicationRough Sets
    EditorsRafael Bello, Duoqian Miao, Rafael Falcon, Michinori Nakata, Alejandro Rosete, Davide Ciucci
    Place of PublicationCham
    PublisherSpringer International Publishing
    Pages225-235
    Number of pages11
    ISBN (Print)9783030527051
    Publication statusPublished - 2020

    Fingerprint

    Dive into the research topics of 'Feature and Label Association Based on Granulation Entropy for Deep Neural Networks'. Together they form a unique fingerprint.

    Cite this