---
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.'
altloc:
- http://www.robotic.dlr.de/Smagt/SmaGroGro94b.ps.gz
chapter: ~
commentary: ~
commref: ~
confdates: 1994
conference: IEEE International Conference on Neural Networks
confloc: Florida
contact_email: ~
creators_id: []
creators_name:
- family: Smagt
given: P. van der
honourific: ''
lineage: ''
- family: Groen
given: F.
honourific: ''
lineage: ''
- family: Groenewoud
given: F. van het
honourific: ''
lineage: ''
date: 1994
date_type: published
datestamp: 1998-07-03
department: ~
dir: disk0/00/00/04/96
edit_lock_since: ~
edit_lock_until: ~
edit_lock_user: ~
editors_id: []
editors_name: []
eprint_status: archive
eprintid: 496
fileinfo: /style/images/fileicons/application_postscript.png;/496/2/SmaGroGro94b.ps
full_text_status: public
importid: ~
institution: ~
isbn: ~
ispublished: pub
issn: ~
item_issues_comment: []
item_issues_count: 0
item_issues_description: []
item_issues_id: []
item_issues_reported_by: []
item_issues_resolved_by: []
item_issues_status: []
item_issues_timestamp: []
item_issues_type: []
keywords: 'neural networks, high-dimensional function approximation, learning, robot arm control'
lastmod: 2011-03-11 08:54:00
latitude: ~
longitude: ~
metadata_visibility: show
note: ~
number: ~
pagerange: 2787-2792
pubdom: FALSE
publication: ~
publisher: IEEE
refereed: FALSE
referencetext: ~
relation_type: []
relation_uri: []
reportno: ~
rev_number: 10
series: ~
source: ~
status_changed: 2007-09-12 16:29:08
subjects:
- comp-sci-neural-nets
- comp-sci-robot
succeeds: ~
suggestions: ~
sword_depositor: ~
sword_slug: ~
thesistype: ~
title: The locally linear nested network for robot manipulation
type: confpaper
userid: 462
volume: ~