The Power of Approximation: A Comparison of Activation Functions
暂无分享,去创建一个
[1] J. Reif,et al. On Threshold Circuits and Polynomial Computation , 1992, SIAM J. Comput..
[2] Ken-ichi Funahashi,et al. On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.
[3] F. Girosi,et al. Networks for approximation and learning , 1990, Proc. IEEE.
[4] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..
[5] D. Newman. Rational approximation to | x , 1964 .
[6] Robert M. Farber,et al. How Neural Nets Work , 1987, NIPS.
[7] H. White,et al. There exists a neural network that does not make avoidable mistakes , 1988, IEEE 1988 International Conference on Neural Networks.
[8] Tomaso A. Poggio,et al. Extensions of a Theory of Networks for Approximation and Learning , 1990, NIPS.
[9] S. M. Carroll,et al. Construction of neural nets using the radon transform , 1989, International 1989 Joint Conference on Neural Networks.
[10] Kurt Hornik,et al. Multilayer feedforward networks are universal approximators , 1989, Neural Networks.
[11] Zhang Wei,et al. Approximation property of multi-layer neural network (MLNN) and its application in nonlinear simulation , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.
[12] B. Irie,et al. Capabilities of three-layered perceptrons , 1988, IEEE 1988 International Conference on Neural Networks.
[13] Georg Schnitger,et al. On the computational power of sigmoid versus Boolean threshold circuits , 1991, [1991] Proceedings 32nd Annual Symposium of Foundations of Computer Science.