Simultaneous evolution of neural network topologies and weights for classificat...

• Author(s): Rocha, Miguel ; Cortez, Paulo, 1971- ; Neves, José
• Date: 2005
• Persistent ID: http://hdl.handle.net/1822/2222
• Origin: RepositóriUM - Universidade do Minho
• Subject(s): Supervised learning; Multilayer perceptrons; Evolutionary algorithms; Ensembles
• Document Type: Conference Object
• Language: English

Description

Artificial Neural Networks (ANNs) are important Data Mining (DM) techniques. Yet, the search for the optimal ANN is a challenging task: the architecture should learn the input-output mapping without overfitting the data and training algorithms tend to get trapped into local minima. Under this scenario, the use of Evolutionary Computation (EC) is a promising alternative for ANN design and training. Moreover, since EC methods keep a pool of solutions, an ensemble can be build by combining the best ANNs. This work presents a novel algorithm for the optimization of ANNs, using a direct representation, a structural mutation operator and Lamarckian evolution. Sixteen real-world classification/regression tasks were used to test this strategy with single and ensemble based versions. Competitive results were achieved when compared with a heuristic model selection and other DM algorithms.