Training a sigmoidal node is hard

Neural Computation

Volumn 11, Issue 5, 1999, Pages 1249-1260

  Hush, Don R ^a  

^a LOS ALAMOS NATIONAL LABORATORY   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0001513581     PISSN: 08997667     EISSN: None     Source Type: Journal    
DOI: 10.1162/089976699300016449     Document Type: Article

References (16)

1. Barron, A. (1991). Approximation and estimation bounds for artificial neural networks. In L. Valiant & M. Warmuth (eds.), Proceedings of the 4th Annual Workshop on Computational Learning Theory (pp. 243-249).
2. Barron, A. (1993). Universal approximation bounds for superpositions of a sigmoidal function. IEEE Transactions on Information Theory, 39(3), 930-945.
3. Baum, E. (1989). A proposal for more powerful learning algorithms. Neural Computation, 1(2), 201-207.
4. Blum, A., & Rivest, R. (1988). Training a 3-node neural network is NP-complete. In Proceedings of the Computational Learning Theory (COLT) Conference (pp. 9-18). San Mateo, CA: Morgan Kaufmann.
5. Breiman, L., & Friedman, J. (1994). Function approximation using ramps. In Snowbird Workshop on Machines That Learn, Snowbird, UT.
6. DasGupta, B., Siegelmann, H., & Sontag, E. (1995). On the complexity of training neural networks with continuous activation functions. IEEE Transactions on Neural Networks, 6(6), 1490-1504.
7. Höffgen, K.-U. (1993). Computational limitations on training sigmoidal neural networks. Information Processing Letters, 46, 269-274.
8. Hush, D., & Home, B. (1998). Efficient algorithms for function approximation with piecewise linear sigmoidal networks. IEEE Transactions on Neural Networks, 9(6), 1129-1141.
9. Jones, L. (1992). A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training. Annals of Statistics, 20, 608-613.
10. Jones, L. (1997). The computational intractibility of training sigmoidal neural networks. IEEE Transactions on Information Theory, 43(1), 167-173.
11. Judd, J. (1990). Neural network design and the complexity of learning. Cambridge, MA: MIT Press.
12. Lin, J.-H., & Vitter, J. S. (1991). Complexity results on learning by neural networks. Machine Learning, 6, 211-230.
13. Maass, W. (1995). Agnostic pac-learning of functions on analog neural nets (Tech. Rep. No. NC-TR-95-002). Graz, Austria: Institute for Theoretical Computer Science.
14. Šíma, J. (1996). Back-propagation is not efficient. Neural Networks, 9(6), 1017-1023.
15. Siu, K.-Y., Roychowdhury, V., & Kailath, T. (1995). Discrete neural computation: A theoretical foundation. Englewood Cliffs, NJ: Prentice Hall.
16. Staley, M. (1995). Learning with piece-wise linear networks. International Journal of Neural Systems, 6(1), 43-59.