Evolution of neural networks for classification and regression

• Author(s): Rocha, Miguel ; Cortez, Paulo, 1971- ; Neves, José
• Date: 2007
• Persistent ID: http://hdl.handle.net/1822/8028
• Origin: RepositóriUM - Universidade do Minho
• Subject(s): Supervised learning; Multilayer perceptrons; Evolutionary algorithms; Lamarckian optimization; Neural network ensembles
• Document Type: Article
• Language: English

Description

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.