TY  - GEN
ID  - cogprints496
UR  - http://cogprints.org/496/
A1  - Smagt, P. van der
A1  - Groen, F.
A1  - Groenewoud, F. van het
Y1  - 1994///
N2  - 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.
PB  - IEEE
KW  - neural networks
KW  -  high-dimensional function approximation
KW  -  learning
KW  -  robot arm control
TI  - The locally linear nested network for robot manipulation
SP  - 2787
AV  - public
EP  - 2792
ER  -

<script src='https://archive-bar.soton.ac.uk/archive-bar.js'></script>
<script src='https://archive-bar.soton.ac.uk/google-analytics.js'></script>