NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
Development of Methodologies for IV and V of Neural NetworksNon-deterministic systems often rely upon neural network (NN) technology to "lean" to manage flight systems under controlled conditions using carefully chosen training sets. How can these adaptive systems be certified to ensure that they will become increasingly efficient and behave appropriately in real-time situations? The bulk of Independent Verification and Validation (IV&V) research of non-deterministic software control systems such as Adaptive Flight Controllers (AFC's) addresses NNs in well-behaved and constrained environments such as simulations and strict process control. However, neither substantive research, nor effective IV&V techniques have been found to address AFC's learning in real-time and adapting to live flight conditions. Adaptive flight control systems offer good extensibility into commercial aviation as well as military aviation and transportation. Consequently, this area of IV&V represents an area of growing interest and urgency. ISR proposes to further the current body of knowledge to meet two objectives: Research the current IV&V methods and assess where these methods may be applied toward a methodology for the V&V of Neural Network; and identify effective methods for IV&V of NNs that learn in real-time, including developing a prototype test bed for IV&V of AFC's. Currently. no practical method exists. lSR will meet these objectives through the tasks identified and described below. First, ISR will conduct a literature review of current IV&V technology. TO do this, ISR will collect the existing body of research on IV&V of non-deterministic systems and neural network. ISR will also develop the framework for disseminating this information through specialized training. This effort will focus on developing NASA's capability to conduct IV&V of neural network systems and to provide training to meet the increasing need for IV&V expertise in such systems.
Document ID
20040027535
Acquisition Source
Goddard Space Flight Center
Document Type
Preprint (Draft being sent to journal)
Authors
Taylor, Brian
(Institute for Scientific Research MA, United States)
Darrah, Marjorie
(Institute for Scientific Research MA, United States)
Date Acquired
August 21, 2013
Publication Date
January 1, 2003
Subject Category
Computer Programming And Software
Funding Number(s)
CONTRACT_GRANT: NAG5-12069
Distribution Limits
Public
Copyright
Other

Available Downloads

There are no available downloads for this record.
No Preview Available