Header logo is

Local dimensionality reduction for locally weighted learning


Conference Paper


Incremental learning of sensorimotor transformations in high dimensional spaces is one of the basic prerequisites for the success of autonomous robot devices as well as biological movement systems. So far, due to sparsity of data in high dimensional spaces, learning in such settings requires a significant amount of prior knowledge about the learning task, usually provided by a human expert. In this paper we suggest a partial revision of the view. Based on empirical studies, it can been observed that, despite being globally high dimensional and sparse, data distributions from physical movement systems are locally low dimensional and dense. Under this assumption, we derive a learning algorithm, Locally Adaptive Subspace Regression, that exploits this property by combining a local dimensionality reduction as a preprocessing step with a nonparametric learning technique, locally weighted regression. The usefulness of the algorithm and the validity of its assumptions are illustrated for a synthetic data set and data of the inverse dynamics of an actual 7 degree-of-freedom anthropomorphic robot arm.

Author(s): Vijayakumar, S. and Schaal, S.
Book Title: International Conference on Computational Intelligence in Robotics and Automation
Pages: 220-225
Year: 1997

Department(s): Autonomous Motion
Bibtex Type: Conference Paper (inproceedings)

Address: Monteray, CA, July10-11, 1997
Cross Ref: p1030
Note: clmc
URL: http://www-clmc.usc.edu/publications/V/vijayakumar-CIRA1997.pdf


  title = {Local dimensionality reduction for locally weighted learning},
  author = {Vijayakumar, S. and Schaal, S.},
  booktitle = {International Conference on Computational Intelligence in Robotics and Automation},
  pages = {220-225},
  address = {Monteray, CA, July10-11, 1997},
  year = {1997},
  note = {clmc},
  crossref = {p1030},
  url = {http://www-clmc.usc.edu/publications/V/vijayakumar-CIRA1997.pdf}