|
|
| Record Number | 3245 |
| Reference Type | Journal Article |
| Author(s) | Edakunni, N. U.;Schaal, S.;Vijayakumar, S. |
| Year | submitted |
| Title | Probabilistic incremental locally weighted learning using randomly varying coefficient model |
| Journal/Conference/Book Title | Machine Learning |
| Keywords | locally weighted learning, bayesian regression, bandwidth adaptation, variational methods, online learning |
Abstract |
We present a Bayesian formulation of locally weighted learning (LWL) using the novel concept of
a randomly varying coefficient model. Based on this, we propose a mechanism for multivariate nonlinear
regression using spatially localised linear models that learns completely independent of each
other, uses only local information and adapts the local model complexity in a data driven fashion. We
derive online updates for the model parameters based on variational Bayesian EM. The evaluation of
the proposed algorithm against other state-of-the-art methods reveal the excellent, robust generalization
performance besides surprising efficiency in time and space complexity. This paper, for the first time,
brings together the computational efficiency and the adaptability of Ônon-competitiveÕ locally weighted
learning schemes and the modelling guarantees of the Bayesian formulation.
|
| Notes | clmc |
| Short Title | Probabilistic incremental locally weighted learning using randomly varying coefficient model |
| Papers are available as Adobe PDF ".pdf" files. Adobe Reader is available for free for all computer platforms.
|
|
|
|
|
Page last modified on August 10, 2006, at 06:47 PM
|
|
