Propagación de errores

Backpropagation

• Rumelhart, D. E., Hinton, G. E. & Williams, R. J. (1986): "Learning internal representations by error propagation." In D. E. Rumelhart & J. L. McClelland (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition, 1: Foundation (pp. 318–362). Cambridge: MIT Press. URL http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6302929
• Werbos, P. J. (1974): "Beyond Regressions: New Tools for Prediction and Analysis in the Behavioral Sciences," PhD Thesis, Harvard University, Cambridge, MA. URL https://www.researchgate.net/publication/35657389
• Finnoff, W. (1994): "Diffusion approximations for the constant learning rate backpropagation algorithm and resistance to local minima." Neural Computation, 6(2):285–295. DOI https://doi.org/10.1162/neco.1994.6.2.285

Propiedades formales de las redes multicapa

• Xiang, C., Ding, S. Q. & Lee, T. H. (2005): "Geometrical interpretation and architecture selection of MLP." IEEE Transactions on Neural Networks, 16(1):84–96. DOI https://doi.org/10.1109/TNN.2004.836197

Redes con una capa oculta

• Cybenko, G. (1989): "Approximation by superpositions of a sigmoid function." Mathematics of Control, Signals, and Systems, 2:303–314. DOI https://doi.org/10.1007/BF02551274 (correction: MCSS 5(4):455, 1992, DOI https://doi.org/10.1007/BF02134016)
• Funahashi, K. (1989): "On the approximate realization of continuous mappings by neural networks." Neural Networks, 2(3):183–192. DOI https://doi.org/10.1016/0893-6080(89)90003-8
• Hornik, K. M., Stinchcombe, M. & White, H. (1989): "Multilayer feedforward networks are universal approximators." Neural Networks, 2:359–366. DOI https://doi.org/10.1016/0893-6080(89)90020-8
• Maiorov, V. & Pinkus, A. (1999): "Lower bounds for approximation by MLP neural networks." Neurocomputing, 25, 81–91. DOI https://doi.org/10.1016/S0925-2312(98)00111-8
• Zhang, X. M., Chen, Y. Q., Ansari, N. & Shi, Y. Q. (2004): "Mini-max initialization for function approximation." Neurocomputing, 57, 389–409. DOI https://doi.org/10.1016/j.neucom.2003.10.014

Redes con dos capas ocultas

• Chester, D. L. (1990): "Why two hidden layers are better than one." In IJCNN'90 Proceedings of International Joint Conference on Neural Networks, pp. 265–268. Washington DC.
• J. de Villiers & E. Barnard (1993): "Backpropagation neural nets with one and two hidden layers," IEEE Transactions on Neural Networks, 4(1):136-141, DOI https://doi.org/10.1109/72.182704
• Tamura, S. & Tateishi, M. (1997): "Capabilities of a four-layered feedforward neural network: four layers versus three." IEEE Transactions on Neural Networks, 8(2):251–255. DOI https://doi.org/10.1109/72.557662
• Huang, G. B. (2003): "Learning capability and storage capacity of two-hidden-layer feedforward networks." IEEE Transactions on Neural Networks, 14(2):274–281. DOI https://doi.org/10.1109/TNN.2003.809401