Title :
Recursive single-layer nets for output error dynamic models
Author_Institution :
Dept. of Electr. & Comput. Syst. Eng., Morash Univ., Clayton, Vic., Australia
fDate :
3/1/1995 12:00:00 AM
Abstract :
An algorithm for training recursive single-layer nets that has been shown to exhibit rapid convergence is presented. Convergence is not guaranteed, but a sufficient condition is given to justify the method. The method is demonstrated on a difficult modeling problem from bioengineering
Keywords :
learning (artificial intelligence); neural nets; bioengineering; output error dynamic models; rapid convergence; recursive single-layer nets; sufficient condition; Biomedical engineering; Convergence; Cost function; Equations; Feedforward neural networks; Iterative algorithms; Least squares approximation; Neural networks; Predictive models; Sufficient conditions;
Journal_Title :
Neural Networks, IEEE Transactions on
