Verification and Validation of Neural Networks for Aerospace Systems

The Dryden Flight Research Center V&V working group and NASA Ames Research Center Automated Software Engineering (ASE) group collaborated to prepare this report. The purpose is to describe V&V processes and methods for certification of neural networks for aerospace applications, particularly adaptive flight control systems like Intelligent Flight Control Systems (IFCS) that use neural networks. This report is divided into the following two sections: Overview of Adaptive Systems and V&V Processes/Methods.

[1]  Philip E. Gill,et al.  Practical optimization , 1981 .

[2]  V. Kvasnicka,et al.  Neural and Adaptive Systems: Fundamentals Through Simulations , 2001, IEEE Trans. Neural Networks.

[3]  Parag A. Pathak,et al.  Massachusetts Institute of Technology , 1964, Nature.

[4]  D. I. Soloway.  Improved convergence for output scaling of a feedforward network with linear output nodes , 1993, IEEE International Conference on Neural Networks.

[5]  Tony R. Martinez,et al.  Digital Neural Networks , 1988, Proceedings of the 1988 IEEE International Conference on Systems, Man, and Cybernetics.

[6]  William H. Press,et al.  Numerical recipes in C , 2002 .

[7]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[8]  John Kaneshige,et al.  INTEGRATED NEURAL FLIGHT AND PROPULSION CONTROL SYSTEM , 2001 .

[9]  John E. Dennis,et al.  Numerical methods for unconstrained optimization and nonlinear equations , 1983, Prentice Hall series in computational mathematics.