1. Multilayer feedforward networks are universal approximators;Hornik;Neural Netw.,1989
2. Approximation by superpositions of a sigmoidal function;Cybenko;Math. Control Syst.,1989
3. D. Rumelhart, G. Hinton, R. Williams, Learning Representations by Back-propagating Errors, Nature.
4. Y. LeCun, B. Boser, J. Denker, D. Henderson, R. Howard, W. Hubbard, L. Jackel, Handwritten digit recognition with a back-propagation network, in: Advances in Neural Information Processing Systems (NIPS 1989), 2, Denver, CO, 1990.
5. Gradient-based learning applied to document recognition;LeCun;Proc. IEEE,1998