A new stochastic learning algorithm using Gaussian white noise sequence, referred to as Subconscious Noise Reaction (SNR), is proposed for a class of discrete-time neural networks with time-dependent connection weights. Unlike the back-propagation-through-time (BTT) algorithm, SNR does not require the synchronous transmission of information backward along connection weights, while it uses only ...

We explore the connection between the concepts “excess” and “duality gap” from epigraphical analysis and optimization, and the functional analytic concepts of weak* and weak compactness. We also discuss briefly the connection with R. C. James’s “sup theorem”.

We study attribute dependencies in a setting of fuzzy logic. Our dependencies are described by formulas A ⇒ B where A and B are fuzzy sets of attributes. The meaning of A ⇒ B is that any two objects that have similar values on attributes from A have also similar values on attributes from B. Our approach generalizes classical functional dependencies from databases and also several approaches to ...

We discuss the quantized theory of a pure-gauge non-abelian vector field (flat connection) as it would appear in a mass term à la Stückelberg. However the paper is limited to the case where only the flat connection is present (no field strength term). The perturbative solution is constructed by using only the functional equations and by expanding in the number of loops. In particular we do not ...