5. Summary
Visualization can help bridge the cognitive gap by representing relationships in the neural and by examining how those relationships evolve. Two-dimensional diagrams, three-dimensional plots, or even 3D simulations can be used to visually compare structures and adaptation of the neural networks. These activities can be used as V&V activities to assess the constraints or limitations of the proposed neural network architecture.
Visualization can aid in both developing and understanding systems involving neural networks. Personnel involved in verifying and validating such systems may have little or no knowledge of the workings of a neural network. Through the use of visualization techniques, such as simple neuron models, the MATLAB Neural Network Toolbox and Simulink, or even 3D visualizations, the understanding can be increased.
This is a preview of subscription content, log in via an institution to check access.
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
Craven, Mark W. and Jude W. Shavlik. 1992. Visualizing Learning and Computation in Artificial Neural Networks. International Journal on Artificial Intelligence Tools 13:399–425.
Freitas, Carla M.D.S., Paulo R.G. Luzzardi, Ricardo A. Cava, Marco Winckler, Marcelo S. Pimenta, Luciana P. Nedel. 2002. On Evaluating Information Visualization Techniques. In Proceeding of Advanced Visual Interfaces. Trento, Italy, May.
Gupta, Pramod and Johann Schumann. 2004. A Tool for Verification and Validation of Neural Network Based Adaptive Controllers for High Assurance Systems. In Proceeding of High Assurance Systems Engineering (HASE). Tampa, FL. April 2004. 277–278.
Hinton, G.E., McClelland, J.L., and Rumelhart, D.E. 1986. Distributed representations. In Parallel Distributed Processing: Explorations in the Microstructure of Cognition, eds. D.E. Rumelhart and J.L. McClelland. Cambridge: MIT Press. 77–109.
Mackall, Dale; Stacy Nelson; and Johann Schumman. 2002. Verification and Validation of Neural Networks for Aerospace Systems. NASA Dryden Flight Research Center and NASA Ames Research Center. June 12.
Mathworks, Inc. 1998. Neural Network User’s Guide (version 3).
Munro, P. 1991. Visualization of 2-D Hidden Unit Space. Technical Report LIS035/IS91003, School of Library and Information Science, University of Pittsburgh, Pittsburgh, PA.
Perhinschi, M. G., G. Campa, M. R. Napolitano, M. Lando, L. Massotti, and M.L. Fravolini. 2002. Modeling and simulation of a fault tolerant flight control system. Submitted to International Journal of Modeling and Simulation in April 2002.
Pratt, L.Y. and Mostwo, J. 1991. Direct Transfer of Learned Information Among Neural Networks. In Proceedings of the Ninth National Conference on Artificial Intelligence, Anaheim, CA. 584–589.
Pratt, L. Y., and Nicodemus, S. 1993. Case Studies in the Use of a Hyperplane Animator for Neural Network Research. In Proceedings of the IEEE International Conference on Neural Networks, IEEE World Congress on Computational Intelligence, 1:78–83.
Soares, Fola. 2002. Users Manual for the Generic Analysis Tool of Neural Network-Based Flight Control systems, Hypersonic Vehicles, Adaptive controllers, and Lyapunov Techniques.
Towell, G.G., Shavlik, J.W., and Noordewier, M.O. 1990. Refinement of Approximately Correct Domain Theories by Knowledge-Based Neural Networks. In Proceedings of the Eighth National Conference on Artificial Intelligence. Boston, MA: MIT Press. 861–866.
Towell, G.G., M.W. Craven, and J.W. Shavlik. 1991. Constructive Induction in Knowledge-Based Neural Networks. In Machine Learning: Proceedings of the Seventh International Workshop. Evanston, IL. Morgan Kaufmann. 213–217.
Vesanto J. 1998. http://www.cis.hut.fi/∼juuso/vrmlsom/index.html.
Vesanto J. 1999. SOM-Based Visualization Methods. Intelligent Data Analysis. 3:111–126.
Wejchert, J., and Tesauro, G. 1990. Neural Network Visualization. In Advances in Neural Information Processing Systems, Vol. 2, 465–472. San Mateo, CA.: Morgan Kaufmann.
Author information
Authors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer Science+Business Media, Inc.
About this chapter
Cite this chapter
Darrah, M. (2006). Neural Network Visualization Techniques. In: Methods and Procedures for the Verification and Validation of Artificial Neural Networks. Springer, Boston, MA. https://doi.org/10.1007/0-387-29485-6_7
Download citation
DOI: https://doi.org/10.1007/0-387-29485-6_7
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-28288-6
Online ISBN: 978-0-387-29485-8
eBook Packages: Computer ScienceComputer Science (R0)