Hierarchial Neural Network Implementation for Forecasting
Abstract
In this paper, a hierarchial neural network architecture for forecasting time series is presented. The architecture is composed of two hierarchial levels using a maximum likelihood competitive learning algorithm. The first level of the system has three experts each using backpropagation and a gating network to partition the input space in order to map the input vectors to the output vectors. The second level of the hierarchial network has an expert using Fuzzy ART for producing the correct trend coming from the first level. The experiments show that the resulting network is capable of forecasting the changes in the input and identifying the trends correctly.
Recommended Citation
M. A. Ozbayoglu and C. H. Dagli, "Hierarchial Neural Network Implementation for Forecasting," IEEE International Conference on Neural Networks - Conference Proceedings, vol. 5, pp. 3184 - 3189, Dec 1994.
Department(s)
Engineering Management and Systems Engineering
Document Type
Article - Conference proceedings
Document Version
Citation
File Type
text
Language(s)
English
Rights
© 2024 The Authors, All rights reserved.
Publication Date
01 Dec 1994
