论文信息 - Neural Networks and Unconstrained Optimization

Neural Networks and Unconstrained Optimization

When performing the unconstrained optimisation of a complicated industrial problem, the main computational time is usually spent in the calculation of the objective function and its derivatives. The calculation of the objective function is usually performed sequentially, so if a parallel processing machine is to be used, then either a number of function evaluations must be calculated in parallel or the sequential calculation of the objective function replaced by a parallel calculation.

L. C. W. Dixon | L. Dixon

[1] Bruce Christianson,et al. Automatic Hessians by reverse accumulation , 1992 .

[2] J. G. Taylor,et al. ARTIFICIAL NEURAL NETWORKS, 2 , 1992 .

[3] Andrew R. Barron,et al. Universal approximation bounds for superpositions of a sigmoidal function , 1993, IEEE Trans. Inf. Theory.

[4] Robert Hecht-Nielsen,et al. The Munificence of High Dimensionality , 1992 .

[5] D. J. Mills,et al. Neural networks and nonlinear optimization i the representation of continuous functions , 1992 .

[6] Dennis W. Ruck,et al. Science of Artificial Neural Networks , 1992 .

[7] David Mills,et al. Neural nets for massively parallel optimization , 1992, Defense, Security, and Sensing.

[8] K. D. Patel,et al. Experience running optimisation algorithms on parallel processing systems , 1984 .

[9] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[10] R. Hecht-Nielsen,et al. Theory of the Back Propagation Neural Network , 1989 .

[11] J. Dennis,et al. Direct Search Methods on Parallel Machines , 1991 .