| Summary: | In this paper we analyse several approaches to the design of Cooperative Algorithms for solving a general problem: That of computing the values of some property over a spatial domain, when these values are constrained (but not uniquely determined) by some observations, and by some a priori knowledge about the nature of the solution (smoothness, for example).
Specifically, we discuss the use of: Variational techniques; stochastic approximation methods for global optimization, and linear threshold networks. Finally, we present a new approach, based on the interconnection of Winner-take-all networks, for which it is possible to establish precise convergence results, including bounds on the rate of convergence.
|
|---|