Title :
A robust model based on space-partitioning method
Author :
Zhang, Liming ; Fan, Weiping
Author_Institution :
Dept. of Electr. Eng., Fudan Univ., Shanghai, China
Abstract :
A new model, called the space-partitioning multilayer perceptron (SP-MLP), is proposed in this paper to resolve classification problems. The number of first-hidden-layer units is determined adaptively, and we introduce a new sub-algorithm to improve the robustness of the network. The results of experiments show that the SP-MLP is more robust than other models. The issue of generalization is also discussed in this paper
Keywords :
generalisation (artificial intelligence); multilayer perceptrons; pattern classification; adaptive determination; classification problems; first-hidden-layer units; generalization; robust model; robustness-enhancing sub-algorithm; space-partitioning algorithm; space-partitioning multilayer perceptron; two-spirals problem; Analytical models; Convergence; Handwriting recognition; Multilayer perceptrons; Neural networks; Neurons; Partial response channels; Partitioning algorithms; Robustness;
Conference_Titel :
Neural Information Processing, 1999. Proceedings. ICONIP '99. 6th International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-5871-6
DOI :
10.1109/ICONIP.1999.844671
