Highly Influenced

@article{Rigler1991RescalingOV, title={Rescaling of variables in back propagation learning}, author={A. K. Rigler and J. M. Irvine and Thomas P. Vogl}, journal={Neural Networks}, year={1991}, volume={4}, pages={225-229} }

- Published 1991 in Neural Networks
DOI:10.1016/0893-6080(91)90006-Q

-Use of the logistic derivative in backward error propagation suggests one source of ill-conditioning to be the decreasing multiplier in the computation of the elements of the gradient at each layer. A compensatory rescaling is suggested, based heuristically upon the expected value of the multiplier. Experimental results demonstrate an order of magnitude improvement in convergence. Keywords--Backward error propagation, Layered networks, Rescaling, Preconditioning.

### Presentations referencing similar topics