Abstract
We study the classification of sonar targets first introduced by Gorman & Sejnowski (1988). We discovered that not only the training set and the test set of this benchmark are both linearly separable, although by different hyperplanes, but that the complete set of patterns, training and test patterns together, is also linearly separable. The distances of the patterns to the separating hyperplane determined by learning with the training set alone, and to the one determined by learning the complete data set, are presented.
Similar content being viewed by others
References
R.P. Gorman and T.J. Sejnowski, “Analysis of hidden units in a layered network trained to classify sonar targets”, Neural Networks, 1: 75–89, 1988.
M. Berthold, “A probabilistic extension for the DDA algorithm”, in IEEE International Conference on Neural Networks, pp. 341–346, Washington, 1996.
M.R. Berthold and J. Diamond, “Boosting the performance of RBF networks with dynamic decay adjustment”, in G. Tesauro, D. Touretzky, and T. Leen, editors, Advances in Neural Information Processing Systems, Vol. 7, pp. 521–528, The MIT Press, 1995.
J. Bruske and G. Sommer, “Dynamic cell structures”, in G. Tesauro, D. Touretzky, and T. Leen, editors, Advances in Neural Information Processing Systems, Vol. 7, pp. 497–504, The MIT Press, 1995.
B. Chakraborty and Y. Sawada, “Fractal connection structure: Effect on generalization supervised feedforward networks”, in IEEE International Conference on Neural Networks, pp. 264–269, Washington, 1996.
M. Karouia, R. Lengellé and T. Denoeux, “Performance analysis of a MLP weight initialization algorithm”, in Michel Verleysen (ed.) European Symposium on Artificial Neural Networks, pp. 347–352, Brussels, 1995, D facto.
A. Roy, S. Govil and R. Miranda, “An algorithm to generate radial basis function (rbf)‐like nets for classification problems”, Neural Networks, 8(2): 179–201, 1995.
A. Roy, L. Kim and S. Mukhopadhyay, “A polynomial time algorithm for the construction and training of a class of multilayer perceptron”, Neural Networks, 6(1): 535–545, 1993.
Y. Shang and B.W. Wha, “A global optimization method for neural networks training”, in IEEE International Conference on Neural Networks, pp. 7–11, Washington, 1996.
Brijesh K. Verma and Jan J. Mulawka, “A new algorithm for feedforward neural networks”, in Michel Verleysen (ed.) European Symposium on Artificial Neural Networks, pp. 359–364, Brussels, 1995, D facto.
M.B. Gordon and D. Berchier, “Minimerror: A perceptron learning rule that finds the optimal weights”, in Michel Verleysen, editor, European Symposium on Artificial Neural Networks, pp. 105–110, Brussels, 1993. D facto.
B. Raffin and M.B. Gordon, “Learning and generalization with minimerror, a temperature dependent learning algorithm”, Neural Computation, 7(6): 1206–1224, 1995.
M. Hoehfeld and S. Fahlman, “Learning with limited numerical precision using the cascade correlation algorithm”, Technical Report CMUCS91130, Carnegie Mellon University, 1991.
J.‐M. Torres Moreno and M. Gordon, “An evolutive architecture coupled with optimal perceptron learning for classification”, in Michel Verleysen (ed.) European Symposium on Artificial Neural Networks, pp. 365–370, Brussels, 1995, D facto.
T.M. Cover, “Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition”, IEEE Transactions on Electronic Computers, EC-14: 326–334, 1965.
E. Gardner, “Maximum storage capacity in neural networks”, Europhysics Letters, 4: 481–485, 1987.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Torres Moreno, J.M., Gordon, M.B. Characterization of the Sonar Signals Benchmark. Neural Processing Letters 7, 1–4 (1998). https://doi.org/10.1023/A:1009605531255
Issue Date:
DOI: https://doi.org/10.1023/A:1009605531255