Abstract
For many important practical applications model transparency is an important requirement. A probabilistic radial basis function (PRBF) network is an effective non-linear classifier, but similarly to most other neural network models it is not straightforward to obtain explanations for its decisions. Recently two general methods for explaining of a model’s decisions for individual instances have been introduced which are based on the decomposition of a model’s prediction into contributions of each attribute. By exploiting the marginalization property of the Gaussian distribution, we show that PRBF is especially suitable for these explanation techniques. By explaining the PRBF’s decisions for new unlabeled cases we demonstrate resulting methods and accompany presentation with visualization technique that works both for single instances as well as for the attributes and their values, thus providing a valuable tool for inspection of the otherwise opaque models.
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
Bishop, C.M.: Neural Networks for Pattern Recognition. Oxford University Press, Oxford (1995)
Constantinopoulos, C., Likas, A.: An incremental training method for the probabilistic RBF network. IEEE Trans. Neural Networks 17(4), 966–974 (2006)
Jacobsson, H.: Rule extraction from recurrent neural networks: A taxonomy and review. Neural Computation 17(6), 1223–1263 (2005)
McLachlan, G., Peel, D.: Finite Mixture Models. John Wiley & Sons, Chichester (2000)
Možina, M., Demšar, J., Kattan, M.W., Zupan, B.: Nomograms for visualization of naive bayesian classifier. In: Boulicaut, J.-F., Esposito, F., Giannotti, F., Pedreschi, D. (eds.) PKDD 2004. LNCS (LNAI), vol. 3202, pp. 337–348. Springer, Heidelberg (2004)
Robnik Šikonja, M., Kononenko, I.: Explaining classifications for individual instances. IEEE Transactions on Knowledge and Data Engineering 20(5), 589–600 (2008)
Setiono, R., Liu, H.: Understanding neural networks via rule extraction. In: Proceedings of IJCAI 1995, pp. 480–487 (1995)
Shapley, L.S.: A value for n-person games. In: Contributions to the Theory of Games, vol. II. Princeton University Press, Princeton (1953)
Titsias, M.K., Likas, A.: Shared kernel models for class conditional density estimation. IEEE Trans. Neural Networks 12(5), 987–997 (2001)
Titsias, M.K., Likas, A.: Class conditional density estimation using mixtures with constrained component sharing. IEEE Trans. Pattern Anal. and Machine Intell. 25(7), 924–928 (2003)
Towell, G.G., Shavlik, J.W.: Extracting refined rules from knowledge-based neural networks. Machine Learning 13(1), 71–101 (1993)
Štrumbelj, E., Kononenko, I.: An Efficient Explanation of Individual Classifications using Game Theory. Journal of Machine Learning Research 11, 1–18 (2010)
Štrumbelj, E., Kononenko, I., Robnik-Šikonja, M.: Explaining instance classifications with interactions of subsets of feature values. Data & Knowledge Engineering 68(10), 886–904 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Robnik-Šikonja, M., Likas, A., Constantinopoulos, C., Kononenko, I., Štrumbelj, E. (2011). Efficiently Explaining Decisions of Probabilistic RBF Classification Networks. In: Dobnikar, A., Lotrič, U., Šter, B. (eds) Adaptive and Natural Computing Algorithms. ICANNGA 2011. Lecture Notes in Computer Science, vol 6593. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-20282-7_18
Download citation
DOI: https://doi.org/10.1007/978-3-642-20282-7_18
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-20281-0
Online ISBN: 978-3-642-20282-7
eBook Packages: Computer ScienceComputer Science (R0)