ATime Series Forecasting Using Neural Network by Modified Adaptive Learning Rates and Initial Values
Yoon Yeo Chang, Lee Sung Duck · The Transactions of the Korea Information Processing Society · 1998
In this work, we consider the forecasting performance between nearal network and Box-Jenkins method for time series data. A modified learning process is developed for neural network approach at time eries data, ie, properly adaptive learning rates selecting by orthogonal arrays and dynamic selecting of initial values using Easton's cotroller box. We can obtain good starting points with dynamic graphics approach. We use real data sets for this study : the Wolf yearly sunspot numbers between 1700 and 1988.