Embedding coupled oscillators into a feedforward architecture for improved time series prediction

The network defined by Hayashi (1994), like many purely recurrent networks, has proven very difficult to train to arbitrary time series. Many recurrent architectures are best suited for producing specific cyclic behaviors. As a result, a hybrid network has been developed to allow for training to mor...

Full description

Saved in:
Bibliographic Details
Published inProceedings of International Conference on Neural Networks (ICNN'96) Vol. 4; pp. 1980 - 1985 vol.4
Main Authors Corwin, E.M., Logar, A.M., Oldham, W.J.B.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1996
Subjects
Accuracy
Cities and towns
Computer networks
Electrocardiography
Feeds
Mathematics
Oscillators
Recurrent neural networks
Testing
Transfer functions
Online AccessGet full text

Cover

More Information
Summary:The network defined by Hayashi (1994), like many purely recurrent networks, has proven very difficult to train to arbitrary time series. Many recurrent architectures are best suited for producing specific cyclic behaviors. As a result, a hybrid network has been developed to allow for training to more general sequences. The network used here is a combination of standard feedforward nodes and Hayashi oscillator pairs. A learning rule, developed using a discrete mathematics approach, is presented for the hybrid network. Significant improvements in prediction accuracy were produced compared to a pure Hayashi network and a backpropagation network. Data sets used for testing the effectiveness of this approach include Mackey-Glass, sunspot, and ECG data. The hybrid models reduced training and testing error in each case by a least 34%.
ISBN:0780332105
9780780332102
DOI:10.1109/ICNN.1996.549205