ePIC

Overcome neural limitations for real world applications by providing confidence values for network predictions

Edit Item Edit Item

General Information:

Citation:
Tagscherer, M. , Kindermann, L. , Lewandowski, A. and Protzel, P. (1999): Overcome neural limitations for real world applications by providing confidence values for network predictions , Proceedings of the Sixth International Conference on Neural Information Processing (ICONIP'99), Perth .
Cite this page as:
Contact Email:
Download:

Supplementary Information:

Abstract:

In this paper we present an incremental construction algorithmfor continuous learning tasks and one of itsspecial features - simultaneous learning of the targetfunction and a confidence value for the system predictions.The basis of the hybrid system is a radial basisfunction (RBF) network layer. The second layer consistsof local models. The two layers are closely combinedwith a strong interaction. The number of RBFneuronsand the number of local models have not to bedetermined in advance. This is one of the main advantagesof the algorithm. Another advantage emphasizedin this paper is the ability to learn the training data distributionsimultaneously to the learning of the targetfunction. The learned data set distribution can be usedas a confidence value for a given network prediction.The development of the described approach is embeddedin a larger project that is primarily concerned withsystem identification tasks for industrial control such assteel processing.

Further Details:

Item Type:
Conference
Authors:
Divisions:
Programs:
Eprint ID:
10403
Imprint
AWI
Policies:
read more
OAI 2.0:
http://epic.awi.de/cgi/oai2
ePIC is powered by:
EPrints 3