A new class of neural networks based on approximate identities for approximation and learning

Proceedings - IEEE International Symposium on Circuits and Systems

Volumn 1, Issue , 1992, Pages 359-362

  Turchetti, C ^a   Conti, M ^a  

^a UNIVERSITÀ POLITECNICA DELLE MARCHE   (Italy)

Author keywords

[No Author keywords available]

Indexed keywords

ALGEBRA;

APPROXIMATE IDENTITIES; INPUT-OUTPUT MAPPING; MULTIVARIATE FUNCTION; THEORETICAL FRAMEWORK; THREE-LAYER;

NETWORK LAYERS;

EID: 84941514469     PISSN: 02714310     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ISCAS.1992.229939     Document Type: Conference Paper

References (6)

1. G. Cybenko, "Approximation by superposition of a sigmoidal function", Math. Control, Systems, Signals, vol. 2, pp. 303-314, 1989.
2. K. Funahashi, "On the approximate realization of continuous mappings by neural networks", Neural Networks, vol. 2, pp. 183-192, 1989.
3. K. Hornik, M. Stinchcombe, H. White, "Multilayer feedforward networks are universal approximators", Neural Networks, vol. 2, pp. 395-403, 1989.
4. T. Poggio, F. Girosi, "Networks for approximation and learning", Proc. of the IEEE, vol. 78, n. 9, p. 1481, 1990.
5. N. E. Cotter, "The Stone-Weierstrass theorem and its application to neural networks", IEEE Trans, on Neural Networks, vol. 1, n. 4, p. 290, Dec. 1990.
6. C. A. Mead, "Analog VLSI and neural systems", Reading, MA: Addison Wesley, 1989.