The computational intractability of training sigmoidal neural networks

IEEE Transactions on Information Theory

Volumn 43, Issue 1, 1997, Pages 167-173

  Jones, Lee K ^a,b  

^a IEEE   (United States)

^b University of Massachusetts Lowell   (United States)

Author keywords

Interpolation; Lipschitzian sigmoid; Neural networks; Np completeness; Training

Indexed keywords

COMPUTATIONAL COMPLEXITY; INTERPOLATION; MATHEMATICAL MODELS; POLYNOMIALS;

LIPSCHITZIAN SIGMOID; TARGET FUNCTION;

NEURAL NETWORKS;

EID: 0030736446     PISSN: 00189448     EISSN: None     Source Type: Journal    
DOI: 10.1109/18.567673     Document Type: Article

References (14)

1. M. Gary and D. Johnson, Computers and Intractability: A Guide to the Theory of NP-Completeness. San Francisco, CA: Freeman, 1979.
2. J. S. Judd, "Complexity of connectionist learning with various node functions." Tech. Rep. 87-60, Univ. of Massachusetts, Amherst, 1987.
3. _, Neural Network Design and the Complexity of Learning. Cambridge, MA: MIT Press, 1990.
4. A.L. Blum and R. L. Rivest, "Training a 3-node neural network is NP-complete" Neural Networks, vol. 5., pp. 117-127, 1992.
5. B. Das Gupta, H. T. Siegelmann, and E. Sontag, "On a learnability question associated to neural networks with continuous activations," in Proc. 7th A.C.M. Conf. on Learning Theory, 1994, pp. 47-56.
6. E. D. Sontag, "Feedforward nets for interpolation and classification," J. Comp. Syst. Sci., vol. 45, pp. 20-48. 1992,
7. K. U. Höffgen, "Computational limitations on training sigmoidal neural networks," Inform. Process. Lett., vol. 46, pp. 269-274, 1993.
8. L. G. Khachian, "A polynomial algorithm in linear programming," Sov. Math.-Dokl., vol. 20, no. 1, 1979.
9. D. S. Johnson and F. P. Preparata, "The densest hemisphere problem," Theor. Comp. Sci., vol. 6, pp. 93-107, 1978.
10. L. K. Jones, "Constructive approximations for neural networks by sigmoidal functions," Proc. IEEE, vol. 78, no. 10, pp. 1586-1589, oct. 1990.
11. Also, "Correction and addition," Proc. IEEE, vol. 79, pp. 242-243, feb. 1991.
12. _, "A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training," Ann. Statist., vol. 20, no. 1, pp. 608-613, 1992.
13. A. R. Barron, "Universal approximation bounds for superpositions of a sigmoidal function," IEEE Trans. Inform. Theory, vol. 39, no. 3, pp. 930-945, may 1993.
14. L. K. Jones, "Good weights and hyperbolic kernels for neural networks, projection pursuit, and pattern classification: Fourier strategies for extracting information from high-dimensional data," IEEE Trans. Inform. Theory, vol. 40, no. 2, pp. 439-454, 1994.