Modeling time-varying processes by unfolding the time domain


Contact
lkindermann [ at ] awi-bremerhaven.de

Abstract

Most current technologies in modeling time varyingprocesses aim to adapt a static model over time in whathas become to be known as continuous learning. Wepropose here a different approach to the same problemdomain that of including the time explicitly in themodeling. An example implementation of this strategy isgiven in form of a multilayer perceptron with explicit timeinput. The performance of this approach is evaluating on abenchmark that was constructed to illustrate typicalproblems in industrial applications.



Item Type
Conference (Conference paper)
Authors
Divisions
Programs
Peer revision
Not peer-reviewed
Publication Status
Published
Event Details
Proceedings of the International Joint Conference on Neural Networks (IJCNN'99), Washington DC..
Eprint ID
10382
Cite as
Kindermann, L. and Trappenberg, T. (1999): Modeling time-varying processes by unfolding the time domain , Proceedings of the International Joint Conference on Neural Networks (IJCNN'99), Washington DC. .


Share

Research Platforms
N/A

Campaigns


Actions
Edit Item Edit Item