We have recently shown that the widely known LMS algorithm is an H OO optimal estimator. The H OO criterion has been introduced, initially in the control theory literature, as a means to ensure robust performance in the face of model uncertainties and lack of statistical information on the exogenous signals. We extend here our analysis to the nonlinear setting often encountered in neural networ...

Since the influential work of Dickerson (1969), there has been considerable discussion of design of crossbreeding experiments, but little detailed treatment of optimisation. Recently, Cunningham and Connolly (1989) and Soelkner and James (1990) have discussed this question, but have used different optimality criteria. Connolly and Cunningham used the sum of sampling variances of estimators, whi...

The identification problem is largely formulated as a problem of finding a plant operator estimate optimal in terms of a specified criterion. The resultant solution permits estimation of the model adequacy. The criterion and the model structure are selected individually for each model. For complex systems the large number of plant parameter interrelations and of external disturbances make a com...

We consider the system of articulators “jaw – tip of the tongue” in order to investigate instant and integral optimality criteria in the variational approach to the solution of speech inverse problem “from total displacement of articulators to their controls”. The required experimental data i.e., coordinates of the tip of the tongue and lower incisor have been measured by the use of the X-ray m...

The independent assignment problem (or the weighted matroid intersection problem) is extended using Dress-Wenzel’s matroid valuations, which are attached to the vertex set of the underlying bipartite graph as an additional weighting. Specifically, the problem considered is: Given a bipartite graph G = (V , V −;A) with arc weight w : A → R and matroid valuations ω and ω− on V + and V − respectiv...

The objective of the research is to study and compare response surface designs: Central composite designs (CCD), BoxBehnken designs (BBD), Small composite designs (SCD), Hybrid designs, and Uniform shell designs (USD) over sets of reduced models when the design is in a spherical region for 3 and 4 design variables. The two optimality criteria ( D and G ) are considered which larger values imply...

Several criteria from the optimal design literature are examined for use with item selection in multidimensional adaptive testing. In particular, it is examined what criteria are appropriate for adaptive testing in which all abilities are intentional, some should be considered as a nuisance, or the interest is in the testing of a composite of the abilities. Both the theoretical analyses and the...