Specification and Construction of the Perceptron Multicapa Model
- 1 January 2020
- book chapter
- Published by IGI Global Scientific Publishing
- p. 118-135
Abstract
The objective of this chapter is to analyze the problem surrounding the task of prognosis with neural networks and the factors that affect the construction of the model, and that often lead to inconsistent results, emphasizing the problems of selecting the training algorithm, the number of neurons in the hidden layer, and input variables. The methodology is to analyze the forecast of time series, due to the growing need for tools that facilitate decision-making, especially in series that, given their characteristics of noise and variability, infer nonlinear dynamics. Neural networks have emerged as an attractive approach to the representation of such behaviors due to their adaptability, generalization, and learning capabilities. Practical evidence shows that the Delta Delta and RProp training methods exhibit different behaviors than expected.Keywords
This publication has 52 references indexed in Scilit:
- Red Neuronal Artificial aplicado para el pronóstico de eventos críticos de PM2.5 en el Valle de Aburra.DYNA, 2019
- Análisis de series de tiempo en el pronóstico de la demanda de almacenamiento de productos perecederosEstudios Gerenciales, 2016
- Aplicación del Modelo ANFIS para Predicción de Series de TiempoLámpsakos, 2013
- Input-variable specification for Neural Networks - An analysis of forecasting low and high time series frequency2009
- TUNING DIVERSITY IN BAGGED ENSEMBLESInternational Journal of Neural Systems, 2000
- Neural modeling for time series: A statistical stepwise method for weight eliminationIEEE Transactions on Neural Networks, 1995
- Some recent developments in non-linear time series modelling, testing, and forecastingInternational Journal of Forecasting, 1992
- First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's MethodNeural Computation, 1992
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- On tests for non‐linearity in time series analysisJournal of Forecasting, 1986