Time Complexity Research on the Second Type Neural Networks of Padé Weight Functions

Abstract:

Time complexity is an important measure of algorithm. The main purpose of this paper is to research the time complexity of the second category of Padé weight function neural network and find out the factors which affect its time complexity. In this paper, firstly, the second category of Padé weight function neural network algorithm is introduced. Then through the analysis of the key steps of the algorithm, the time complexity is given. After MATLAB simulation, the experimental results verify the theoretical analysis of the results. Therefore, its time complexity is related to input dimension, output dimension and the number of training samples.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 2667-2670
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.2667
• Online since: July 2014
• Authors: Dai Yuan Zhang*, Lei Yang
• Keywords: Neural Network (NN), Newton Interpolation, Padé Weight Function, Time Complexity

References

[1] Zhang Dai-yuan. New Theories and Methods on Neural Networks [M]. Beijing: Tsinghua University Press, (2006).

[2] William H. Press, Saul A. Teukolsky. Numerical Algorithms in C [M]. Beijing：Electronic Industry Press, (2004).

[3] G. Fournodavlos, V. Nestoridis. Generic approximation of functions by their Padé approximants.

[4] Guido Claessens. On the Newton-Padé approximation problem [J]. Journal of Approximation Theory, 1978, (22): 150-160.

DOI: 10.1016/0021-9045(78)90062-x

[5] George A. Baker. Essentials of Padé Approximants [M]. New York: Academic Press, (1975).