Neural networks are family statistical learning algorithms and structures and are used to estimate or approximate functions and pattern classification. The Neural network system is constructed through interconnected neurons and training weights. The paper will present the improvement of recognition rate, recognition time and hardware overhead through introducing TMR technology into the conventional RBF neural network which is a simple neural network only consisting of three layers.
This research was supported by the Undergraduate Research Opportunities Program (UROP).
Radial Basis Function (RBF) Neural Networks Based on the Triple Modular Redundancy Technology (TMR).
Retrieved from the University of Minnesota Digital Conservancy,
Content distributed via the University of Minnesota's Digital Conservancy may be subject to additional license and use restrictions applied by the depositor.