Learning by Error-driven Decomposition

Abstract

In this paper we describe a new selforganizing decomposition technique for learning high-dimensional mappings. Problem decomposition is performed in an error-driven manner, such that the resulting subtasks (patches) are equally well approximated. Our method combines an unsupervised learning scheme (Feature Maps [Koh84]) with a nonlinear approximator (Backpropagation [RHW86]). The resulting learning system is more stable and effective in changing environments than plain backpropagation and much more powerful than extended feature maps as proposed by [RS88, RMS89]. Extensions of our method give rise to active exploration strategies for autonomous agents facing unknown environments.