On Reducing Learning Time in Context-Dependent Mappings

This paper presents an approach to overcoming the slow convergence problems often associated with learning complex nonlinear mappings. The mappings are learned in a context-dependent manner so that complex problems are decomposed into simpler subproblems corresponding to different contexts. While no general conditions for determining applicability of the method have been found, its power is illustrated through experiments in controlling simulated robot manipulators in two and three degrees of freedom (DOF's). The experiments also indicate that the method shows promising scaleup properties.