PSOM network: learning with few examples

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 pro...

Full description

Saved in:
Bibliographic Details
Main Author: Walter, J.A.
Format: Conference Proceeding
Language:English
Subjects:
Computer science
Costs
Kinematics
Learning systems
Manipulators
Neural networks
Orbital robotics
Organizing
Robot sensing systems
Training data
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:1050-4729
2577-087X
DOI:10.1109/ROBOT.1998.680619