Treffer: On-line training of neural networks : A sliding window approach for the levenberg-marquardt algorithm

Title:
On-line training of neural networks : A sliding window approach for the levenberg-marquardt algorithm
Source:
Artificial intelligence and knowledge engineering applications : a bioinspired approach (Las Palmas, 15-18 June 2005. Part II)Lecture notes in computer science. :577-585
Publisher Information:
Berlin: Springer, 2005.
Publication Year:
2005
Physical Description:
print, 11 ref
Original Material:
INIST-CNRS
Document Type:
Konferenz Conference Paper
File Description:
text
Language:
English
Author Affiliations:
Escola Superior de Tecnologia de Setúbal do Instituto Politécnico de Setùbal, Departamento de Engenharia Electrotécnica, Campus do IPS, Estefanilha, 2914-508 Setùbal, Portugal
Escola Superior de Tecnologia de Castelo Branco, Departamento de Engenharia Electrotécnica, Av. Empresário, 6000 Castelo Branco, Portugal
Departamento de Electrónica e Telecomunicaçôes, Universidade de Aveiro, 3810 - 193 Aveiro, Portugal
ISSN:
0302-9743
Rights:
Copyright 2005 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Computer science; theoretical automation; systems
Accession Number:
edscal.17010814
Database:
PASCAL Archive

Weitere Informationen

In the Neural Network universe, the Backpropagation and the Levenberg-Marquardt are the most used algorithms, being almost consensual that the latter is the most effective one. Unfortunately for this algorithm it has not been possible to develop a true iterative version for on-line use due to the necessity to implement the Hessian matrix and compute the trust region. To overcome the difficulties in implementing the iterative version, a batch sliding window with Early Stopping is proposed, which uses a hybrid Direct/Specialized evaluation procedure. The final solution is tested with a real system.