Memorias de investigación
Communications at congresses:
New Artificial Metaplasticity MLP Results on Standard Data Base
Year:2009

Research Areas
  • Artificial intelligence,
  • Automatic,
  • Processing and signal analysis

Information
Abstract
This paper tests a novel improvement in neural network training by implementing Metaplasticity Multilayer Perceptron (MMLP) Neural Networks (NNs), that are based on the biological property of metaplasticity. Artificial Metaplasticity bases its efficiency in giving more relevance to the less frequent patterns and subtracting relevance to the more frequent ones. The statistical distribution of training patterns is used to quantify how frequent a pattern is. We model this interpretation in the NNs training phase. Wisconsin breast cancer database (WBCD) was used to train and test MMLP. Our results were compared to recent research results on the same database, proving to be superior or at least an interesting alternative
International
Si
Congress
IWANN 09
960
Place
Salamanca
Reviewers
Si
ISBN/ISSN
978-3-642-02477-1
10.1007/978-3-642-02478-8
Start Date
10/06/2009
End Date
12/06/2009
From page
174
To page
179
Bio-Inspired Systems : Computational and Ambient Intelligence. LCNS 5517
Participants

Research Group, Departaments and Institutes related
  • Creador: Grupo de Investigación: Grupo de Automatización en Señal y Comunicaciones (GASC)
  • Departamento: Ingeniería de Circuitos y Sistemas
  • Departamento: Señales, Sistemas y Radiocomunicaciones