Summary: 1024 IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS--I: FUNDAMENTAL THEORY AND APPLICATIONS, VOL. 49, NO. 7, JULY 2002
Application-Level Robustness and Redundancy in Linear
Abstract--The paper quantifies the degradation in performance of a
linear model induced by perturbations affecting its identified parameters.
We extend sensitivity analyses available in the literature, by considering a
generalization-based figure of merit instead of the inaccurate training one.
Effective off-line techniques reducing the impact of perturbations on gen-
eralization performance are introduced to improve the robustness of the
model. It is shown that further robustness can be achieved by optimally re-
distributing the information content of the given model over topologically
more complex linear models of neural network type. Despite the additional
robustness achievable, it is shown that the price we have to pay might be
too high and the additional resources would be better used to implement a
-ary modular redundancy scheme.
Index Terms--Linear computation, linear neural networks, perturbation
analysis, robustness, sensitivity.
Application robustness, defined as the ability to provide a contained