Document Type
Conference Proceeding
Publication Date
3-1993
Publication Title
IEEE Conference on Neural Networks
Abstract
The optimal interpolative (OI) classification network is extended to include fault tolerance and make the network more robust to the loss of a neuron. The OI Net has the characteristic that the training data are fit with no more neurons than necessary. Fault tolerance further reduces the number of neurons generated during the learning procedure while maintaining the generalization capabilities of the network. The learning algorithm for the fault tolerant OI Net is presented in a recursive format, allowing for relatively short training times. A simulated fault tolerant OI Net is tested on a navigation satellite selective problem.
Repository Citation
Simon, Daniel J. and El-Sherief, Hossny, "A Fault-Tolerant Optimal Interpolative Net" (1993). Electrical and Computer Engineering Faculty Publications. 173.
https://engagedscholarship.csuohio.edu/enece_facpub/173
Original Citation
D. Simon and H. El-Sherief. (1993). A Fault-Tolerant Optimal Interpolative Net. IEEE Conference on Neural Networks, 825-830, doi: 10.1109/ICNN.1993.298665.
DOI
10.1109/ICNN.1993.298665
Volume
2
