PSOM network: learning with few examples

Abstract

We discuss the "parametrized self-organizing maps" (PSOM) as a learning method for rapidly creating high-dimensional, continuous mappings. By making use of available topological information the PSOM shows excellent generalization capabilities from a small set of training data. The PSOM provides, as an important generalization, a flexibly usable continuous associate memory. Task specifications for redundant manipulators often leave the problem of picking one action from a subspace of possible alternatives. The PSOM approach offers a flexible and compact form to select various constraint and target functions previously associated. We present application results for learning several kinematic relations of a hydraulic robot finger in a single PSOM module. Based on only 27 data points, the PSOM learns the inverse kinematic with a mean positioning accuracy of 1% of the entire workspace. Also, the PSOM learns various ways to resolve the redundancy problem for positioning a 4-DOF manipulator.