Fine-tuning artificial neural networks automatically

• Type: Article in International Conference Proceedings Book
• Date: 2007

Authors

Francisco Reinaldo (Author) FEUP; Rui Camacho (Author) FEUP; Luís P. Reis (Author) FEUP; Demétrio Renó Magalhães (Author) Other

Conference proceedings International

Title: EUROPEAN COMPUTING CONFERENCE

Pages: 39-43

EUROPEAN COMPUTING CONFERENCE

Scientific classification

FOS: Engineering and technology > Electrical engineering, Electronic engineering, Information engineering

CORDIS: Technological sciences > Engineering > Knowledge engineering

Other information

DOI: 10.1007/978-0-387-84814-3_5

Abstract (EN): To get the most out of powerful tools expert knowledge is often required. Experts are the ones with the suitable knowledge to tune the tools¿ parameters. In this paper we assess several techniques which can automatically fine tune ANN parameters. Those techniques include the use of GA and Stratified Sampling. The tuning includes the choice of the best ANN structure and the best network biases and their weights. Empirical results achieved in experiments performed using nine heterogeneous data sets show that the use of the proposed Stratified Sampling technique is advantageous.

Language: English

Type (Professor's evaluation): Scientific

No. of pages: 5