Abstract
Online Adaptive Systems in general, and learning neural nets in particular cannot be validated using traditional verification and validation techniques, because they evolve over time, and past learning data influences their behavior. In this paper we discuss a framework for reasoning about online adaptive systems, and see how this framework can be used to perform V\&V on such systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
J.R. Abrial. The B Book: Assigning Programs to Meanings. Cambridge University Press, 1996.
Ch. Alexander, D. DelGobbo, V. Cortellessa, A. Mili, and M. Napolitano. Modeling the fault tolerant capability of a flight control system: An exercise in SCR specifications. In Proceedings, Langley Formal Methods Conference, Hampton, VA, June 2000.
H. Ammar, B. Cukic, C. Fuhrman, and Mili. A comparative analysis of hardware and software fault tolerance: Impact on software reliability engineering. Annals of Software Engineering, 10, 2000.
A. Avizienis. The n-version approach to fault tolerant software. IEEE Trans, on Software Engineering, 11(12), December 1985.
R.J. Back and J. von Wright. Refinement Calculus: A Systematic Introduction. Graduate Texts in Computer Science. Springer Verlag, 1998.
N. Boudriga, F. Elloumi, and A. Mili. The lattice of specifications: Applications to a specification methodology. Formal Aspects of Computing, 4:544–571, 1992.
M. A. Boyd, J. Schumann, G. Brat, D. Giannakopoulou, B. Cukic, and A. Mili. Ifcs project: Validation and verification (v&v) process guide for software and neural nets. Technical report, NASA Ames Research Center, September 2001.
Ch. Brink, W. Kahl, and G. Schmidt. Relational Methods in Computer Science. Springer Verlag, New York, NY and Heidelberg, Germany, 1997.
Rodney A. Canfield. Meet and join within the lattice of set partitions. Technical report, The University of Georgia, Athens, 2001.
M. Caudill. Driving solo. AI Expert, pages 26--30, September 1991.
C. H. Dagli, S. Lammers, and M. Vellanki. Intelligent scheduling in manufacturing using neural networks. Journal of Neural Network Computing, pages 4––10, 1991.
J. Dean. Timing the testing of cots software products. In First International ICSE Workshop on Testing Distributed Component Based Systems, Los Angeles, CA, May 1999.
Jules Desharnais, Ali Mili, and Thanh Tung Nguyen. Refinement and demonic semantics. In Brink et al. [8], chapter 11, pages 166--183.
E.W. Dijkstra, A Discipline of Programming. Prentice Hall, 1976.
D. Bernard et al. Final report on the remote agent experiment. In NMP DS-1 Technology Validation Symposium, Pasadena, CA, February 2000.
B. Fritzke. Growing self-organizing networks — why. In European Symposium on Artificial Neural Networks, pages 61––72, Brussels, Belgium, 1996.
LiMin Fu. Neural Networks in Computer Intelligence. McGraw Hill, 1994.
P. Gardiner and C.C. Morgan. Data refinement of predicate transformers. Theoretical Computer Science, 87:143–162, 1991.
D. Del Gobbo and B. Cukic. Validating on-line neural networks. Technical report, Lane Department of Computer Science and Electrical Engineering, West Virginia University, December 2001.
D. Gries. The Science of programming. Springer Verlag, 1981.
H. Hecht, M. Hecht, and D. Wallace. Toward more effective testing for highassurance systems. In Proceedings of the 2nd IEEE High Assurance Systems Engineering Workshop, Washington, D.C., August 1997.
Internet. Program verification system. Technical report, SRI International Computer Science Laboratory, 1997.
J. A. Leonard, M. A. Kramer, and L. H. Ungar. Using radial basis functions to approximate a function and its error bounds. IEEE Transactions on Neural Networks, 3(4):624––627, July 1991.
M. Lowry, M. Boyd, and D. Kulkarni. Towards a theory for integration of mathematical verification and empirical testing. In Proceedings, 13th IEEE International Conference on Automated Software Engineering, pages 322––331, Honolulu, HI, October 1998. IEEE Computer Society.
Z. Manna. A Mathematical Theory of Computation. McGraw Hill, 1974.
H.D. Mills, V.R. Basili, J.D. Gannon, and D.R. Hamlet. Structured Programming: A Mathematical Approach. Allyn and Bacon, Boston, Ma, 1986.
C.C. Morgan. Programming from Specifications. International Series in Computer Sciences. Prentice Hall, London, UK, 1998.
M. Napolitano, G. Molinaro, M. Innocenti, and D. Martinelli. A complete hardware package for a fault tolerant flight control system using on-line learning neural networks. IEEE Control Systems Technology, January 1998.
M. Napolitano, C. D. Neppach, V. Casdorph, S. Naylor, M. Innocenti, and G Silvestri. A neural network-based scheme for sensor failure detection, identification and accomodation. AIAA Journal of Control and Dynamics, 18(6):1280––1286, 1995.
D.B. Parker. Learning logic. Technical Report S81-64, Stanford University,1982.
G. E. Peterson. A foundation for neural network verification and validation. SPIE Science of Artificial Neural Networks II, 1966:196--207, 1993.
D. K. Pradhan. Fault Tolerant Computing: Theory and Practice. Prentice-Hall, Englewood Cliffs, NJ, 1986.
B. Randall. System structure for software fault tolerance. IEEE Transactions on Software Engineering, SE-1(2), 1975.
Orna Raz. Validation of online artificial neural networks ---an informal classification of related approaches. Technical report, NASA Ames Research Center, Moffet Field, CA, 2000.
D.E. Rumelhart, G.E. Hinton, and R.J. Williams. Learning internal representations by error propagation. In Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Volume I: Foundations. MIT Press, Cambridge, MA, 1986.
D.P. Siewiorek and R. S. Swarz. The Theory and Practice of Reliable System Design. Digital Press, Bedford, Mass, 1982.
Boeing Staff. Intelligent flight control: Advanced concept program. Technical report, The Boeing Company, 1999.
P.J. Werbos. Beyond regression: New tools for prediction and analysis in the behavioral sciences. Technical report, Harvard University, 1974.
J. Von Wright. A lattice theoretical basis for program refinement. Technical report, Dept. of Computer Science, Abo Akademi, Finland, 990.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer Science+Business Media New York
About this chapter
Cite this chapter
Mili, A., Cukic, B., Liu, Y., Ayed, R.B. (2003). Towards the Verification and Validation of Online Learning Adaptive Systems. In: Khoshgoftaar, T.M. (eds) Software Engineering with Computational Intelligence. The Springer International Series in Engineering and Computer Science, vol 731. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-0429-0_7
Download citation
DOI: https://doi.org/10.1007/978-1-4615-0429-0_7
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-5072-9
Online ISBN: 978-1-4615-0429-0
eBook Packages: Springer Book Archive