Buscar
Mostrando ítems 21-30 de 30
Enhancing LSTM for sequential image classification by modifying data aggregation
(IEEE, 2021)
Contribución a congreso / Biltzarrerako ekarpena,
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, ...
Replacing pooling functions in convolutional neural networks by linear combinations of increasing functions
(Elsevier, 2022)
Artículo / Artikulua,
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 ...
d-Choquet integrals: Choquet integrals based on dissimilarities
(Elsevier, 2020)
info:eu-repo/semantics/article,
The paper introduces a new class of functions from [0,1]n to [0,n] called d-Choquet integrals. These functions are a generalization of the 'standard' Choquet integral obtained by replacing the difference in the definition ...
T-overlap t-migrative functions: a generalization of migrativity in t-overlap functions
(Universidad Distrital Francisco José de Caldas (Colombia), 2020)
info:eu-repo/semantics/article,
Este artículo introduce una generalización de funciones migrativas por extensión de la condición de la operación producto aplicada en las variables. Más específicamente, en lugar de exigir multiplicar la variable x por un ...
Optimizando desviaciones moderadas ponderadas para interfaces cerebro ordenador
(Universidad de Málaga, 2021)
Contribución a congreso / Biltzarrerako ekarpena,
Las interfaces cerebro-ordenador (BCI) basadas en el análisis de Electroencefalografía (EEG) están compuestas por varios elementos para procesar y clasificar las señales de entrada del cerebro. Una fase relevante de estos ...
Extensión multidimensional de la integral de Choquet discreta y su aplicación en redes neuronales recurrentes
(Universidad de Málaga, 2021)
Contribución a congreso / Biltzarrerako ekarpena,
En este trabajo presentamos una definición de la integral de Choquet discreta n-dimensional, para fusionar datos vectoriales. Como aplicación, utilizamos estas nuevas integrales de Choquet discretas multidimensionales en ...
On some classes of directionally monotone functions
(Elsevier, 2020)
info:eu-repo/semantics/article,
In this work we consider some classes of functions with relaxed monotonicity conditions generalizing some other given classes of fusion functions. In particular, directionally increasing aggregation functions (called also ...
Abstract homogeneous functions and consistently influenced/disturbed multi-expert decision making
(IEEE, 2021)
info:eu-repo/semantics/article,
In this paper we propose a new generalization for the notion of homogeneous functions. We show some properties and how it appears in some scenarios. Finally we show how this generalization can be used in order to provide ...
Neuro-inspired edge feature fusion using Choquet integrals
(Elsevier, 2021)
Artículo / Artikulua,
It is known that the human visual system performs a hierarchical information process in which early vision cues (or primitives) are fused in the visual cortex to compose complex shapes and descriptors. While different ...
Type-(2, k) overlap indices
(IEEE, 2022)
Artículo / Artikulua,
Automatic image detection is one of the most im- portant areas in computing due to its potential application in numerous real-world scenarios. One important tool to deal with that is called overlap indices. They were ...