A Formal Method for Verification and Validation of Neural Network High Assurance Systems

Award Information
Agency:
National Aeronautics and Space Administration
Branch
n/a
Amount:
$99,963.00
Award Year:
2004
Program:
STTR
Phase:
Phase I
Contract:
NNA04AA20C
Agency Tracking Number:
030126
Solicitation Year:
2003
Solicitation Topic Code:
T1.01
Solicitation Number:
n/a
Small Business Information
PROLOGIC, INC
1000 Technology Drive, Fairmont, WV, 26554-8824
Hubzone Owned:
N
Socially and Economically Disadvantaged:
Y
Woman Owned:
N
Duns:
941134876
Principal Investigator:
Marjorie Darrah
Principal Investigator
() -
mdarrah@isr.us
Business Contact:
Ken Snyder
Business Official
(304) 363-1157
ksnyder@prologic-inc.com
Research Institution:
Institue for Scientific Research, Inc.
Not E Available
320 Adams Street, PO Box 2720
Fairmont, WV, 26555
(304) 368-9300
Nonprofit college or university
Abstract
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.

* information listed above is at the time of submission.

Agency Micro-sites

US Flag An Official Website of the United States Government