Universal approximation with Fuzzy ART and Fuzzy ARTMAP. Verzi, S., Heileman, G., Georgiopoulos, M., & Anagnostopoulos, G. C. In Neural Networks, 2003. Proceedings of the International Joint Conference on, volume 3, pages 1987-1992 vol.3, July, 2003.
doi  abstract   bibtex   
A measure of success for any learning algorithm is how useful it is in a variety of learning situations. Those learning algorithms that support universal function approximation can theoretically be applied to a very large and interesting class of learning problems. Many kinds of neural network architectures have already been shown to support universal approximation. In this paper, we will provide a proof to show that Fuzzy ART augmented with a single layer of perceptrons is a universal approximator. Moreover, the Fuzzy ARTMAP neural network architecture, by itself, will be shown to be a universal approximator.
@InProceedings{Verzi2003,
  author    = {Verzi, S.J. and Heileman, G.L. and Georgiopoulos, Michael and Anagnostopoulos, Georgios C.},
  title     = {Universal approximation with Fuzzy ART and Fuzzy ARTMAP},
  booktitle = {Neural Networks, 2003. Proceedings of the International Joint Conference on},
  year      = {2003},
  volume    = {3},
  pages     = {1987-1992 vol.3},
  month     = {July},
  abstract  = {A measure of success for any learning algorithm is how useful it is
	in a variety of learning situations. Those learning algorithms that
	support universal function approximation can theoretically be applied
	to a very large and interesting class of learning problems. Many
	kinds of neural network architectures have already been shown to
	support universal approximation. In this paper, we will provide a
	proof to show that Fuzzy ART augmented with a single layer of perceptrons
	is a universal approximator. Moreover, the Fuzzy ARTMAP neural network
	architecture, by itself, will be shown to be a universal approximator.},
  doi       = {10.1109/IJCNN.2003.1223712},
  issn      = {1098-7576},
  keywords  = {ART neural nets;function approximation;fuzzy neural nets;learning (artificial intelligence);neural net architecture;perceptrons;adaptive resonance theory;fuzzy ART;fuzzy ARTMAP;learning algorithms;machine learning;neural network architecture;perceptrons;universal function approximation;Approximation algorithms;Computer science;Function approximation;Fuzzy logic;Fuzzy neural networks;Machine learning;Machine learning algorithms;Neural networks;Resonance;Subspace constraints},
}

Downloads: 0