Affiliation:
1. University Simón Bolívar, Colombia
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.
Reference73 articles.
1. Red Neuronal Artificial aplicado para el pronóstico de eventos críticos de PM2.5 en el Valle de Aburra.
2. First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's Method
3. Prediction of the maintenance performance cost in dwellings and building sites located in Spain using multilayer perceptrons.;Dyna (Bilbao),2019
4. Evolutionary Algorithms for Neural Network Design and Training.;J.Branke;Proceedings of the First Nordic Workshop on Genetic Algorithms and its Applications,1995
5. TUNING DIVERSITY IN BAGGED ENSEMBLES