288 pp. per issue
6 x 9, illustrated
2014 Impact factor:

Neural Computation

June 1, 2000, Vol. 12, No. 6, Pages 1285-1292
(doi: 10.1162/089976600300015358)
© 2000 Massachusetts Institute of Technology
Relationships Between the A Priori and A Posteriori Errors in Nonlinear Adaptive Neural Filters
Article PDF (133.55 KB)

The lower bounds for the a posteriori prediction error of a nonlinear predictor realized as a neural network are provided. These are obtained for a priori adaptation and a posteriori error networks with sigmoid nonlinearities trained by gradient-descent learning algorithms. A contractivity condition is imposed on a nonlinear activation function of a neuron so that the a posteriori prediction error is smaller in magnitude than the corresponding a priori one. Furthermore, an upper bound is imposed on the learning rate η so that the approach is feasible. The analysis is undertaken for both feedforward and recurrent nonlinear predictors realized as neural networks.