Towards the verification and validation of online learning systems: general framework and applications

Online adaptive systems cannot be certified using traditional testing and proving methods, because these methods rely on assumptions that do not hold for such systems. In this paper, we discuss a framework for reasoning about online adaptive systems, and see how this framework can be used to perform the verification of these systems. In addition to the framework, we present some preliminary results on concrete neural network models.

[1]  P. Werbos,et al.  Beyond Regression : "New Tools for Prediction and Analysis in the Behavioral Sciences , 1974 .

[2]  Bernd Fritzke,et al.  Growing self-organizing networks - Why ? , 1996, ESANN.

[3]  Harlan D. Mills,et al.  Cleanroom Software Engineering , 1987, IEEE Software.

[4]  Dhiraj K. Pradhan,et al.  Fault-tolerant computing: theory and techniques; vol. 1 , 1986 .

[5]  Jules Desharnais,et al.  Refinement and Demonic Semantics , 1997, Relational Methods in Computer Science.

[6]  Algirdas Avizienis,et al.  The N-Version Approach to Fault-Tolerant Software , 1985, IEEE Transactions on Software Engineering.

[7]  Edsger W. Dijkstra,et al.  A Discipline of Programming , 1976 .

[8]  LiMin Fu,et al.  Neural networks in computer intelligence , 1994 .

[9]  H. Hecht,et al.  Toward more effective testing for high assurance systems , 1997, Proceedings 1997 High-Assurance Engineering Workshop.

[10]  Wolfram Kahl,et al.  Relational Methods in Computer Science , 1997, Advances in Computing Sciences.

[11]  Carroll Morgan,et al.  Programming from specifications , 1990, Prentice Hall International Series in computer science.

[12]  Ali Mili,et al.  Towards the Verification and Validation of Online Learning Adaptive Systems , 2003 .

[13]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[14]  Hany H. Ammar,et al.  A comparative analysis of hardware and software fault tolerance: Impact on software reliability engineering , 2000, Ann. Softw. Eng..

[15]  Brad Seanor,et al.  A complete hardware package for a fault tolerant flight control system using online learning neural networks , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[16]  J. Mark.  Introduction to radial basis function networks , 1996 .

[17]  David Gries,et al.  The Science of Programming , 1981, Text and Monographs in Computer Science.

[18]  Ali Mili,et al.  On the lattice of specifications: Applications to a specification methodology , 2005, Formal Aspects of Computing.

[19]  Henk Sol,et al.  Proceedings of the 54th Hawaii International Conference on System Sciences , 1997, HICSS 2015.

[20]  John C. Dean,et al.  Timing the Testing of COTS Software Products , 1999 .

[21]  Jean-Raymond Abrial,et al.  The B-book - assigning programs to meanings , 1996 .

[22]  George W. Ernst,et al.  A program verification system , 1976, ACM '76.

[23]  Harlan D. Mills,et al.  Structured programming - theory and practice , 1979, The systems programming series.

[24]  Michael R. Lowry,et al.  Towards a theory for integration of mathematical verification and empirical testing , 1998, Proceedings 13th IEEE International Conference on Automated Software Engineering (Cat. No.98EX239).