Recent studies involving nonlinear discrimination problems suggest that stimuli in human associative learning are represented configurally with narrow generalization, such that presentation of stimuli that are even slightly dissimilar to stored configurations weakly activate these configurations. The authors note that another well-known set of findings in human associative learning, cue-interac...

We investigate a new class of nonlinear control systems of O.D.E., which are not feedback linearizable in general. Our class is a generalization of the well-known feedback linearizable systems, and moreover it is a generalization of the triangular (or pure-feedback) forms studied before. The definition of our class is global, and coordinate-free, which is why the problem of the equivalence is s...

In this study criterion of maximum profit intensity for transportation problems, in contrast to the known criteria of minimum expenses or minimum time for transportation, is considered. This criterion synthesizes financial and time factors and has real economic sense. According to the purpose of this paper, the algorithm of the solution of such a transportation problem is constructed. It is sho...

We prove existence of positive solutions to a nonlinear fractional boundary value problem. Then, under some mild assumptions on the nonlinear term, we obtain a smart generalization of Lyapunov’s inequality. The new results are illustrated through examples.

We study in this paper lower bounds for the generalization error of models derived from multi-layer neural networks, regime where size layers is commensurate with number samples training data. derive explicit general biased estimators, cases two-layered networks. For linear activation function, bound asymptotically tight. In nonlinear case, we provide a comparison our an empirical stochastic gr...