es | en | pt | fr
    • Presentación
    • Países
    • Instituciones
    • Participa
        JavaScript is disabled for your browser. Some features of this site may not work without it.
        Ver ítem 
        •   Inicio
        • Colombia
        • Universidades
        • Universidad Simón Bolívar (Colombia)
        • Ver ítem
        •   Inicio
        • Colombia
        • Universidades
        • Universidad Simón Bolívar (Colombia)
        • Ver ítem

        Estimation of the optimal number of neurons in extreme learning machine using simulated annealing and the golden section

        Fecha
        2023
        Registro en:
        17426596
        https://hdl.handle.net/20.500.12442/13163
        https://doi.org/10.1088/1742-6596/2515/1/012003
        https://repositorioslatinoamericanos.uchile.cl/handle/2250/8356774
        Autor
        Gelvez-Almeida, E
        Mora, M
        Huérfano-Maldonado, Y
        Salazar-Jurado, E
        Martínez-Jeraldo, N
        Lozada-Yavina, R
        Baldera-Moreno, Y
        Tobar, L
        Institución
        • Universidad Simón Bolívar (Colombia)
        Resumen
        Extreme learning machine is a neural network algorithm widely accepted in the scientific community due to the simplicity of the model and its good results in classification and regression problems; digital image processing, medical diagnosis, and signal recognition are some applications in the field of physics addressed with these neural networks. The algorithm must be executed with an adequate number of neurons in the hidden layer to obtain good results. Identifying the appropriate number of neurons in the hidden layer is an open problem in the extreme learning machine field. The search process has a high computational cost if carried out sequentially, given the complexity of the calculations as the number of neurons increases. In this work, we use the search of the golden section and simulated annealing as heuristic methods to calculate the appropriate number of neurons in the hidden layer of an Extreme Learning Machine; for the experiments, three real databases were used for the classification problem and a synthetic database for the regression problem. The results show that the search for the appropriate number of neurons is accelerated up to 4.5× times with simulated annealing and up to 95.7× times with the golden section search compared to a sequential method in the highest-dimensional database.
        Materias
        Extreme Learning Machine
        Classification and regression problems
        Digital image processing
        Neural networks
        Simulated
        Sequential method

        Mostrar el registro completo del ítem


        Red de Repositorios Latinoamericanos
        + de 8.000.000 publicaciones disponibles
        500 instituciones participantes
        Dirección de Servicios de Información y Bibliotecas (SISIB)
        Universidad de Chile
        Ingreso Administradores
        Colecciones destacadas
        • Tesis latinoamericanas
        • Tesis argentinas
        • Tesis chilenas
        • Tesis peruanas
        Nuevas incorporaciones
        • Argentina
        • Brasil
        • Colombia
        • México
        Dirección de Servicios de Información y Bibliotecas (SISIB)
        Universidad de Chile
        Red de Repositorios Latinoamericanos | 2006-2018
         

        EXPLORAR POR

        Instituciones
        Fecha2011 - 20202001 - 20101951 - 20001901 - 19501800 - 1900

        Explorar en Red de Repositorios

        Países >
        Tipo de documento >
        Fecha de publicación >
        Instituciones >

        Red de Repositorios Latinoamericanos
        + de 8.000.000 publicaciones disponibles
        500 instituciones participantes
        Dirección de Servicios de Información y Bibliotecas (SISIB)
        Universidad de Chile
        Ingreso Administradores
        Colecciones destacadas
        • Tesis latinoamericanas
        • Tesis argentinas
        • Tesis chilenas
        • Tesis peruanas
        Nuevas incorporaciones
        • Argentina
        • Brasil
        • Colombia
        • México
        Dirección de Servicios de Información y Bibliotecas (SISIB)
        Universidad de Chile
        Red de Repositorios Latinoamericanos | 2006-2018