Local output gamma feedback neural network

Onder Uluyol, Magdi Ragheb, Sylvian R. Ray

Research output: Contribution to conferencePaperpeer-review


A theory is introduced for a multi-layered Local Output Gamma Feedback Neural Network (LOGF-NN) within the Locally Recurrent Globally Feedforward neural networks paradigm. It is developed for the classification and prediction tasks for spatio-temporal systems, and allows the representation of different time scales through the incorporation of a gamma memory. The update equations for the feedforward and temporal weights and parameters are derived through the Back-propagation Through Time (BTT) learning algorithm. As a demonstration, it is applied to the benchmark problem of single-step sunspot series prediction, and is compared to other neural network (Weight Elimination Neural Network: WNET) and statistical (Linear and Threshold AutoRegressive: TAR) methods. As a measure of prediction accuracy, the Average Relative Variance (ARV) is used. The proposed LOGF-NN approach's performance is comparable to the TAR method and outperforms the Linear AR and the WNET approaches.

Original languageEnglish (US)
Number of pages6
StatePublished - 1998
EventProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3) - Anchorage, AK, USA
Duration: May 4 1998May 9 1998


OtherProceedings of the 1998 IEEE International Joint Conference on Neural Networks. Part 1 (of 3)
CityAnchorage, AK, USA

ASJC Scopus subject areas

  • Software


Dive into the research topics of 'Local output gamma feedback neural network'. Together they form a unique fingerprint.

Cite this