A note on the convergence of quantizers.
The paper deals with the stability of the fundamental equation of information of multiplicative type. It is proved that the equation in question is stable in the sense of Hyers and Ulam under some assumptions. This result is applied to prove the stability of a system of functional equations that characterizes the recursive measures of information of multiplicative type.
A new algorithm for training feedforward multilayer neural networks is proposed. It is based on recursive least squares procedures and U-D factorization, which is a well-known technique in filter theory. It will be shown that due to the U-D factorization method, our algorithm requires fewer computations than the classical RLS applied to feedforward multilayer neural network training.