Browsing Artículos, Comunicaciones, Libros by Author "Cabezas Olivenza, Mireya"
Now showing items 1-4 of 4
-
A Study of Learning Issues in Feedforward Neural Networks
Teso Fernández de Betoño, Adrián ; Zulueta Guerrero, Ekaitz; Cabezas Olivenza, Mireya; Teso Fernández de Betoño, Daniel ; Fernández Gámiz, Unai (MDPI, 2022-09-05)When training a feedforward stochastic gradient descendent trained neural network, there is a possibility of not learning a batch of patterns correctly that causes the network to fail in the predictions in the areas adjacent ... -
Dynamical Analysis of a Navigation Algorithm
Cabezas Olivenza, Mireya; Zulueta Guerrero, Ekaitz; Sánchez Chica, Ander; Teso Fernández de Betoño, Adrián ; Fernández Gámiz, Unai (MDPI, 2021-12-02)There is presently a need for more robust navigation algorithms for autonomous industrial vehicles. These have reasonably guaranteed the adequate reliability of the navigation. In the current work, the stability of a ... -
Modification of Learning Ratio and Drop-Out for Stochastic Gradient Descendant Algorithm
Teso Fernández de Betoño, Adrián ; Zulueta Guerrero, Ekaitz; Cabezas Olivenza, Mireya; Fernández Gámiz, Unai; Botana Martínez de Ibarreta, Carlos (MDPI, 2023-02-28)The stochastic gradient descendant algorithm is one of the most popular neural network training algorithms. Many authors have contributed to modifying or adapting its shape and parametrizations in order to improve its ... -
Stability Analysis for Autonomous Vehicle Navigation Trained over Deep Deterministic Policy Gradient
Cabezas Olivenza, Mireya; Zulueta Guerrero, Ekaitz; Sánchez Chica, Ander; Fernández Gámiz, Unai; Teso Fernández de Betoño, Adrián (MDPI, 2022-12-27)The Deep Deterministic Policy Gradient (DDPG) algorithm is a reinforcement learning algorithm that combines Q-learning with a policy. Nevertheless, this algorithm generates failures that are not well understood. Rather ...