@InProceedings{SambattiAnLuCaShCa:2012:MPMeAu,
               author = "Sambatti, Sabrina Bergoch Monteiro and Anochi, Juliana Aparecida 
                         and Luz, Eduardo F. Pacheco da and Carvalho, Adenilson R. and 
                         Shiguemori, Elcio Hideiti and Campos Velho, Haroldo Fraga de",
          affiliation = "{Instituto Nacional de Pesquisas Espaciais (INPE)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)} and {} and SERPRO and 
                         {Instituto de Estudos Avan{\c{c}}ado (IEAv)} and {Instituto 
                         Nacional de Pesquisas Espaciais (INPE)}",
                title = "MPCA Meta-Heuristics for automatic architecture optimization of a 
                         supervised artificial neural network",
            booktitle = "Proceedings...",
                 year = "2012",
         organization = "World Congress on Computational Mechanics, 10. (WCCM).",
             abstract = "Artificial neural networks (ANN) has been studied intensively, but 
                         there still are many unresolved issues. The search and definition 
                         of an optimal architecture remains a very relevant ANN research 
                         topic. The search space of neural network topology, each point 
                         represents a possible architecture. Associating each point to a 
                         performance level relies on the a priori establishment of some 
                         optimality criterion. Here, a new meta-heuristics, multi-particle 
                         collision algorithm (MPCA) was applied to design an optimum 
                         architecture for a supervised ANN. The MPCA optimization algorithm 
                         emulates a collision process of multiple particles inspired in 
                         processes of a neutron traveling in a nuclear reactor. The 
                         multilayer perceptron (MLP) was the neural network adopted here, 
                         and backpropagation strategy was used for calculating of the 
                         weight of connections to the MLP-NN. The MLP-NN configured by this 
                         optimal or inverse designs was applied to predict the seasonal 
                         mesoscale climate. The dataset for trainning is obtained from 
                         NCEP-NOAA reanalysis and from a metherological model. In order to 
                         reduce the dimension of the search space to find the optimized 
                         ANN, it is considered the following: three activation functions, 
                         up to three hidden layers, and up to 32 neurons per hidden layer. 
                         The comparison is performed between the ANN configuration obtained 
                         by automatic process and another configuration proposed by a human 
                         specialist.",
  conference-location = "S{\~a}o Paulo",
      conference-year = "2012",
                label = "lattes: 2720072834057575 2 SambattiAnLuCaShCa:2012:MPMeAu",
             language = "en",
           targetfile = "sambatti_mpca.pdf",
        urlaccessdate = "30 abr. 2024"
}