Multilayer feedforward networks are universal approximators
暂无分享，去创建一个
[1] V. Tikhomirov. On the Representation of Continuous Functions of Several Variables as Superpositions of Continuous Functions of one Variable and Addition , 1991 .
[2] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..
[3] H. White,et al. Universal approximation using feedforward networks with non-sigmoid hidden layer activation functions , 1989, International 1989 Joint Conference on Neural Networks.
[4] R. Hecht-Nielsen,et al. Theory of the Back Propagation Neural Network , 1989 .
[5] H. White,et al. There exists a neural network that does not make avoidable mistakes , 1988, IEEE 1988 International Conference on Neural Networks.
[6] C. Lee Giles,et al. Nonlinear dynamics of artificial neural systems , 1987 .
[7] Maureen Caudill,et al. IEEE First International Conference on Neural Networks : Sheraton Harbor Island East, San Diego, California, June 21-24, 1987 , 1987 .
[8] R. Hecht-Nielsen. Kolmogorov''s Mapping Neural Network Existence Theorem , 1987 .
[9] R. J. Williams,et al. The logic of activation functions , 1986 .
[10] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .
[11] W. Rudin. Principles of mathematical analysis , 1964 .