|Title: Robotic Hand-Eye Coordination using Multi-Resolution Linear Perceptron Representation Proceedings of the 1994 Groningen Student Conference on Computer Science|
|Written by: Smagt P van der, Groen F, Groenewoud F van het|
|on pages: 85--92|
|Editor: H. M. Groenboom and H. W. Klijn Hesselink and M. M. Lankhorst|
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; these representations are essentially coded as nodes in a tree. 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. An essential property of the method is its adaptivity through continuous learning. In particular, approximations at different levels of the tree are trained on sets of learning samples which have different temporal histories.