Abstract
Inversion of a neural network trained on some classification problem has been an important issue related to the explanation of the neural classification function. Inversion based on Interval Analysis (IA) [1] showed that a reliable estimation of the neural network domain of validity is feasible and a number of quantitative issues arise from this inversion. This paper deals with the investigation of these quantitative issues and more precisely with those concerning the evaluation of the neural network classification function in terms of generalization, comparison of different network models and classification accuracy. Preliminary experimental results indicate that the IA-based inversion can offer a solid basis towards reliable evaluation of the neural classification function.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adam, S.P., Karras, D.A., Magoulas, G.D., Vrahatis, M.N.: Reliable estimation of a neural network’s domain of validity through interval analysis based inversion. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1–8, July 2015
Bourlard, H., Wellekens, C.J.: Links between markov models and multilayer perceptrons. IEEE Trans. Pattern Anal. Mach. Intell. 12(12), 1167–1178 (1990)
Courrieu, P.: Three algorithms for estimating the domain of validity of feedforward neural networks. Neural Netw. 7(1), 169–174 (1994)
Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. Wiley, New York (1973)
Eberhart, R., Dobbins, R.: Designing neural network explanation facilities using genetic algorithms. In: 1991 IEEE International Joint Conference on Neural Networks, vol. 2, pp. 1758–1763, November 1991
Gish, H.: A probabilistic approach to the understanding and training of neural network classifiers. In: International Conference on Acoustics, Speech, and Signal Processing, vol. 3, pp. 1361–1364, April 1990
Hampshire II, J.B., Pearlmutter, B.A.: Equivalence proofs for multilayer perceptron classifiers and the Bayesian discriminant function. In: Proceedings of 1990 Connectionist Models Summer School, vol. 1, pp. 159–172, April 1991
Hassoun, M.H.: Fundamentals of Artificial Neural Networks. MIT Press, Cambridge (1995)
Haykin, S.: Neural Networks a Comprehensive Foundation, 2nd edn. Prentice-Hall, Upper Saddle River (1999)
Jaulin, L., Kieffer, M., Didrit, O., Walter, E.: Applied Interval Analysis. With Examples in Parameter and State Estimation, Robust Control and Robotics. Springer, London (2001)
Jaulin, L., Walter, E.: Set Inversion Via Interval Analysis for nonlinear bounded-error estimation. Automatica 29(4), 1053–1064 (1993)
Jensen, C., Reed, R., Marks, R., El-Sharkawi, M., Jung, J.B., Miyamoto, R., Anderson, G., Eggen, C.: Inversion of feedforward neural networks: algorithms and applications. Proc. IEEE 87(9), 1536–1549 (1999)
Kearfott, R.B.: Interval computations: introduction, uses, and resources. Euromath Bull. 2(1), 95–112 (1996)
Kindermann, J., Linden, A.: Inversion of neural networks by gradient descent. Parallel Comput. 14(3), 277–286 (1990)
Lippmann, R.P.: Pattern classification using neural networks. IEEE Commun. Mag. 27(11), 47–50 (1989)
Lu, B.L., Kita, H., Nishikawa, Y.: Inverting feedforward neural networks using linear and nonlinear programming. IEEE Trans. Neural Netw. 10(6), 1271–1290 (1999)
Reed, R., Marks, R.: An evolutionary algorithm for function inversion and boundary marking. In: IEEE International Conference on Evolutionary Computation, vol. 2, pp. 794–797, November 1995
Richard, M., Lippmann, R.: Neural network classifiers estimate Bayesian a posteriori probabilities. Neural Comput. 3(4), 461–483 (1991)
Rump, S.M.: INTLAB - INTerval LABoratory. In: Csendes, T. (ed.) Developments in Reliable Computing, pp. 77–104. Kluwer Academic, Dordrecht (1999)
Saad, E.W., Wunsch II, D.C.: Neural network explanation using inversion. Neural Netw. 20(1), 78–93 (2007)
Theodoridis, S., Pikrakis, A., Koutroumbas, K., Kavouras, D.: Introduction to Pattern Recognition: A MATLAB Approach. Academic Press, Burlington (2010)
Thrun, S.B.: Extracting provably correct rules from artificial neural networks. Technical report IAI-TR-93-5, Institut fur Informatik III, Bonn, Germany (1993)
Tornil-Sin, S., Puig, V., Escobet, T.: Set computations with subpavings in MATLAB: the SCS toolbox. In: 2010 IEEE International Symposium on Computer-Aided Control System Design (CACSD), pp. 1403–1408, September 2010
Acknowledgments
The authors would like to thank the anonymous reviewers for their comments and suggestions on earlier draft of the manuscript.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Adam, S.P., Likas, A.C., Vrahatis, M.N. (2017). Interval Analysis Based Neural Network Inversion: A Means for Evaluating Generalization. In: Boracchi, G., Iliadis, L., Jayne, C., Likas, A. (eds) Engineering Applications of Neural Networks. EANN 2017. Communications in Computer and Information Science, vol 744. Springer, Cham. https://doi.org/10.1007/978-3-319-65172-9_27
Download citation
DOI: https://doi.org/10.1007/978-3-319-65172-9_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-65171-2
Online ISBN: 978-3-319-65172-9
eBook Packages: Computer ScienceComputer Science (R0)