Enhancing LSTM for sequential image classification by modifying data aggregation
Fecha
2021Autor
Versión
Acceso abierto / Sarbide irekia
Tipo
Contribución a congreso / Biltzarrerako ekarpena
Versión
Versión aceptada / Onetsi den bertsioa
Impacto
|
10.1109/ICECET52533.2021.9698795
Resumen
Recurrent Neural Networks (RNN) model sequential information and are commonly used for the analysis of time series. The most usual operation to fuse information in RNNs is the sum. In this work, we use a RNN extended type, Long Short-Term Memory (LSTM) and we use it for image classification, to which we give a sequential interpretation. Since the data used may not be independent to each other, we ...
[++]
Recurrent Neural Networks (RNN) model sequential information and are commonly used for the analysis of time series. The most usual operation to fuse information in RNNs is the sum. In this work, we use a RNN extended type, Long Short-Term Memory (LSTM) and we use it for image classification, to which we give a sequential interpretation. Since the data used may not be independent to each other, we modify the sum operator of an LSTM unit using the n-dimensional Choquet integral, which considers possible data coalitions. We compare our methods to those based on usual aggregation functions, using the datasets Fashion-MNIST and MNIST. [--]
Materias
Long short-term Memory,
Recurrent neural network,
Sequential image classification,
Aggregation functions,
Choquet integral
Editor
IEEE
Publicado en
[IEEE].: 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET). IEEE, 2021, 1 - 6, 978-1-6654-4231-2
Departamento
Universidad Pública de Navarra. Departamento de Estadística, Informática y Matemáticas /
Nafarroako Unibertsitate Publikoa. Estatistika, Informatika eta Matematika Saila
Versión del editor
Entidades Financiadoras
This work has been funded by the Agencia Estatal de Investigación (España) under the project PID2019-108392GB-I00 (AEI/10.13039/ 501100011033), by the Immigration Policy and Justice Department of the Government of Navarre-Tracasa Instrumental and the Grant VEGA 1/0267/21 (Slovakia). info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2017-2020/PID2019-108392GB-I00.