Evolution of neural networks for classification and regression

Although Artificial Neural Networks (ANNs) are important Data Mining techniques, the search for the optimal ANN is a challenging task: the ANN should learn the input-output mapping without overfitting the data and training algorithms may get trapped in local minima. The use of Evolutionary Computati...

Full description

Bibliographic Details
Main Author: Rocha, Miguel (author)
Other Authors: Cortez, Paulo (author), Neves, José (author)
Format: article
Language:eng
Published: 2007
Subjects:
Supervised learning
Multilayer perceptrons
Evolutionary algorithms
Lamarckian optimization
Neural network ensembles
Science & Technology
Online Access:http://hdl.handle.net/1822/8028
Country:Portugal
Oai:oai:repositorium.sdum.uminho.pt:1822/8028
Description
Summary:Although Artificial Neural Networks (ANNs) are important Data Mining techniques, the search for the optimal ANN is a challenging task: the ANN should learn the input-output mapping without overfitting the data and training algorithms may get trapped in local minima. The use of Evolutionary Computation (EC) is a promising alternative for ANN optimization. This work presents two hybrid EC/ANN algorithms: the first evolves neural topologies while the latter performs simultaneous optimization of architectures and weights. Sixteen real-world tasks were used to test these strategies. Competitive results were achieved when compared with a heuristic model selection and other Data Mining algorithms.

Similar Items