Examinando por Autor "Gelvez-Almeida, Elkin"
Mostrando 1 - 4 de 4
Resultados por página
Opciones de ordenación
Ítem La interacción social como proceso de encuentro o desencuentro en el aprendizaje académico de los adolescentes(Universidad Francisco de Paula Santander, 2020) Vera-Angarita, Maryori Liliana; Ortega-Ortega, Jhorman Yarokssi; Ramirez-Martinez, Carolina; Gelvez-Almeida, Elkin; Hernández-Niño, Andrea LisbethEl presente artículo de resultados aborda el aprendizaje académico en la edad adolescente como un proceso fundamental para determinar los aspectos que minimizan el rendimiento desde la interacción con padres, profesores y compañeros de curso. Se destacan las rupturas comunicativas con los padres, el desinterés académico del grupo y la mediación de los aprendizajes por los asesores de tareas. Para ello se realizó una investigación centrada en los análisis teóricos del aprendizaje social con Vygotsky, Bandura y las teorías ecológicas, las cuales permiten explorar el interés del colectivo para optimizar los aprendizajes individuales. Metodológicamente se trabajó bajo un enfoque cualitativo, con un enfoque fenomenológico y un alcance de tipo descriptivo. La muestra estuvo constituida por 30 estudiantes, sus padres y 5 docentes de octavo grado del Colegio Sagrado Corazón de Jesús de Cúcuta. Las técnicas e instrumentos de recolección de datos implementados fueron la entrevista por medio de un guion semi-estructurado y la observación directa de tipo participante monitoreada a través del diario de campo, mientras que el análisis de información se realizó mediante la triangulación por actores. Este estudio fenomenológico permitió comprender el aprendizaje social como elemento fundamental para mejorar el rendimiento académico.Ítem A Parallel Computing Method for the Computation of the Moore–Penrose Generalized Inverse for Shared-Memory Architectures(Institute of Electrical and Electronics Engineers (IEEE), 2023) Gelvez-Almeida, Elkin; Barrientos, Ricardo; Vilches, Karina; Mora, MarcoThe computation of the Moore–Penrose generalized inverse is a commonly used operation in various fields such as the training of neural networks based on random weights. Therefore, a fast computation of this inverse is important for problems where such neural networks provide a solution. However, due to the growth of databases, the matrices involved have large dimensions, thus requiring a significant amount of processing and execution time. In this paper, we propose a parallel computing method for the computation of the Moore–Penrose generalized inverse of large-size full-rank rectangular matrices. The proposed method employs the Strassen algorithm to compute the inverse of a nonsingular matrix and is implemented on a shared-memory architecture. The results show a significant reduction in computation time, especially for high-rank matrices. Furthermore, in a sequential computing scenario (using a single execution thread), our method achieves a reduced computation time compared with other previously reported algorithms. Consequently, our approach provides a promising solution for the efficient computation of the Moore–Penrose generalized inverse of large-size matrices employed in practical scenarios.Ítem Parallel ensemble of a randomization-based online sequential neural network for classification problems using a frequency criterion(Nature, 2024) Gelvez-Almeida, Elkin; Barrientos, Ricardo; Vilches, Karina; Mora, MarcoRandomization-based neural networks have gained wide acceptance in the scientific community owing to the simplicity of their algorithm and generalization capabilities. Random vector functional link (RVFL) networks and their variants are a class of randomization-based neural networks. RVFL networks have shown promising results in classification, regression, and clustering problems. For real-world applications, learning algorithms that can train with new samples over previous results are necessary because of to the constant generation of problems related to large-scale datasets. Various online sequential algorithms, commonly involving an initial learning phase followed by a sequential learning phase, have been proposed to address this issue. This paper presents a training algorithm based on multiple online sequential random vector functional link (OS-RVFL) networks for large-scale databases using a shared memory architecture. The training dataset is distributed among p OS-RVFL networks, which are trained in parallel using p threads. Subsequently, the test dataset samples are classified using each trained OS-RVFL network. Finally, a frequency criterion is applied to the results obtained from each OS-RVFL network to determine the final classification. Additionally, an equation was derived to reasonably predict the total training time of the proposed algorithm based on the learning time in the initial phase and the time scaling factor compared to the sequential learning phase. The results demonstrate a drastic reduction in training time because of data distribution and an improvement in accuracy because of the adoption of the frequency criterion.Ítem A Review on Large-Scale Data Processing with Parallel and Distributed Randomized Extreme Learning Machine Neural Networks(MDPI, 2024) Gelvez-Almeida, Elkin; Mora, Marco; Barrientos, Ricardo; Hernández García, Ruber; Vilches, Karina; Vera, MiguelThe randomization-based feedforward neural network has raised great interest in the scientific community due to its simplicity, training speed, and accuracy comparable to traditional learning algorithms. The basic algorithm consists of randomly determining the weights and biases of the hidden layer and analytically calculating the weights of the output layer by solving a linear overdetermined system using the Moore–Penrose generalized inverse. When processing large volumes of data, randomization-based feedforward neural network models consume large amounts of memory and drastically increase training time. To efficiently solve the above problems, parallel and distributed models have recently been proposed. Previous reviews of randomization-based feedforward neural network models have mainly focused on categorizing and describing the evolution of the algorithms presented in the literature. The main contribution of this paper is to approach the topic from the perspective of the handling of large volumes of data. In this sense, we present a current and extensive review of the parallel and distributed models of randomized feedforward neural networks, focusing on extreme learning machine. In particular, we review the mathematical foundations (Moore–Penrose generalized inverse and solution of linear systems using parallel and distributed methods) and hardware and software technologies considered in current implementations.