A Formal Method for Verification and Validation of Neural Network High Assurance Systems
Our proposed innovation is to develop neural network (NN) rule extraction technology to a level where it can be incorporated into a software tool, we are calling NNRules, which captures a trained neural network?s decision logic and uses it as a basis for verification and validation (V&V) of the neural network. This formalism has never been attempted. The significance of the NNRules innovation is that: ? The National Aeronautics and Space Administration, the Department of Defense, the Department of Energy, and the Federal Aviation Administration are currently researching the potential of neural networks in mission- and safety-critical systems. ? High assurance neural network applications require rigorous verification and validation techniques. ? The adaptive and ?black box? characteristics of neural networks make verification and validation of neural networks practically intractable. ? Rule-based systems have a more visible, and potentially human readable, decision logic that supports a robust set of verification techniques. ? Neural network rule extraction research has developed algorithms that translate a neural network into an equivalent set of rules. NNRules embeds this technology in a generally usable tool that will dramatically increase the ability to V&V high assurance neural networks.
Small Business Information at Submission:
Marjorie A. Darrah
Research Institution Information:
1000 Technology Drive Fairmont, WV 26554
Number of Employees:
Institute for Scientific Research, Inc.
320 Adams Street, PO Box 2720
Fairmont, WV 26555
Paul E. Parker, III
Domestic nonprofit research organization