creators_name: Smagt, P. van der
creators_name: Groen, F.
creators_name: Groenewoud, F. van het
type: confpaper
datestamp: 1998-07-03
lastmod: 2011-03-11 08:54:00
metadata_visibility: show
title: The locally linear nested network for robot manipulation
ispublished: pub
subjects: comp-sci-neural-nets
subjects: comp-sci-robot
full_text_status: public
keywords: neural networks, high-dimensional function approximation, learning, robot arm control
abstract: We present a method for accurate representation of high-dimensional unknown functions from random samples drawn from its input space. The method builds representations of the function by recursively splitting the input space in smaller subspaces, while in each of these subspaces a linear approximation is computed. The representations of the function at all levels (i.e., depths in the tree) are retained during the learning process, such that a good generalisation is available as well as more accurate representations in some subareas. Therefore, fast and accurate learning are combined in this method. The method, which is applied to hand-eye coordination of a robot arm, is shown to be superior to other neural networks.
date: 1994
date_type: published
publisher: IEEE
pagerange: 2787-2792
refereed: FALSE
citation:   Smagt, P. van der and Groen, F. and Groenewoud, F. van het  (1994) The locally linear nested network for robot manipulation.  [Conference Paper]     
document_url: http://cogprints.org/496/2/SmaGroGro94b.ps