Abstract
This paper introduces the behaviour of transparency of computational intelligence (CI) models. Transparency reveals to end users the underlying reasoning process of the agent embodying CI models. This is of great benefit in applications (e.g. data mining, entertainment and personal robotics) with humans as end users because it increases their trust in the decisions of the agent and their acceptance of its results. Our integrated approach, wherein rules are just one of other transparency factors (TF), differs from previous related efforts which have focused mostly on generation of comprehensible rules as explanations. Other TF include degree of confidence measure and visualization of principal features. The transparency quotient is introduced as a measure of the transparency of models based on these factors. The transparency enabled generalized exemplar model has been developed to demonstrate the TF and transparency concepts introduced in this paper.
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
Salzberg, S. A nearest hyperrectangle learning method. In Machine Learning 1991; 6(3): 251–276.
Zimmermann, H-J., Tselentis, G., Van Someren, M., & Dounias G. Advances in CI and Learning: Methods and Applications. Kluwer Academic Publishers, 2002
Garcez d’Avila, A. S., Broda, K. B., & Gabbay, D. M. Neural-Symbolic Learning Systems: Foundations and Applications. Springer-Verlag, 2002
Carpenter, G.A., Grossberg, S., Markuzon, N., Reynolds, J.H., & Rosen, D.B. Fuzzy ARTMAP: A Neural Netw. Archit. for Incremental Supervised Learning of Analog Multidimensional Maps. IEEE Trans. Neur. Netw. 1992; 3(5): 698–712
Carpenter, G. & Grossberg, S. A Massively Parall Archit. for a Self Orgnz. Neur. Pattern Recogn. Machine. Comp. Visn, Graphes, and Img. Proc. 1987;37: 54–115
Tsakonas, A., Dounias, G., & Tselentis, G. Using Fuzzy Rules in Multilayer Percept. Neur. Netw. for Multiresolution Proc. Signals: A Real World Applic. in Stock Ex. Mark. In Proc. of Sym. on Comp. Intell., and Learning 2000; 154–170
Cooper, J.W. & Byrd, R.J.: Lexical Navigation: Visually Prompted Query Expans. and Refinem. In Proc. 2nd ACM Infi Conf. Digit. Libr 1997; 237–246
Roussinov, D. & Ramsey, M. Inform. Forage through Adaptive Visualiz. In Proc. of the 3rd ACM Conference on Digital Libraries 303–304. Pittsburgh, PA. 1998
McCormick, B.H., DeFanti T.A. & Brown M.D. ed. Visualization in Scientific Computing, Computer Graphics 1987; 21:6
Joliffe, I.T. Principal Components Analysis. Springer-Verlag 1986
Martin, B. Instance-Based learning: Nearest Neighbor with Generalization. Master Thesis, University of Waikato, Hamilton, New Zealand 1995
Wettschereck, D. & Dietterich, T.G. An experimental comparison of the nearest-neighbour and nearest-hyperrect. algorithms. Machine Learning 1995; 19:5–27
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag London Limited
About this paper
Cite this paper
Owotoki, P., Mayer-Lindenberg, F. (2007). Transparency of Computational Intelligence Models. In: Bramer, M., Coenen, F., Tuson, A. (eds) Research and Development in Intelligent Systems XXIII. SGAI 2006. Springer, London. https://doi.org/10.1007/978-1-84628-663-6_29
Download citation
DOI: https://doi.org/10.1007/978-1-84628-663-6_29
Publisher Name: Springer, London
Print ISBN: 978-1-84628-662-9
Online ISBN: 978-1-84628-663-6
eBook Packages: Computer ScienceComputer Science (R0)