1 January 2019 in Information Fusion
MNMaria Do Carmo Nicoletti
1 December 2011 in Information Sciences
1 October 2013 in Information Sciences
1 January 2022 in Journal of Petroleum Science and Engineering
SBSérgio Ferreira Batista
1 October 2008 in Neurocomputing
1 January 2007 in International Journal of Innovative Computing and Applications
MNMaria Do Carmo Nicoletti
Unlike conventional Neural Network (NN) algorithms that require the definition of the NN architecture before learning starts, Constructive Neural Network (CoNN) algorithms enable the network architecture to be constructed along with the learning process. This paper presents and discusses the results of an empirical evaluation of seven two-class CoNN algorithms, namely Tower, Pyramid, Tiling, Upstart, Shift, Perceptron Cascade (PC) and Partial Target Inversion (PTI) in 12 knowledge domains. The way each particular algorithm approaches the growing of the network determines their differences. This paper also presents and analyses empirical results of five multiclass CoNN algorithms in five knowledge domains, namely MTower, MPyramid, MTiling, MUpstart and MPerceptron Cascade, which can be considered extensions of their two-class counterparts. Results obtained with the Pocket with the Ratchet Modification (PRM) algorithm, with its multiclass version, the PRMWTA algorithm and with the back propagation algorithm, are presented for comparison.