Abstract
Spiral structures are one of the most difficult patterns to classify. In this paper, some important characteristics of the two-spiral problem are discussed. The paper discusses the reasons why linear and non-linear approaches have difficulties with classifying such data. The paper focusses on how structural information about spirals can be useful in providing critical information to a neural network for their recognition. Results are presented on neural network solutions to the classical two-spiral problem by extracting structural and rotational information from the spiral training data.
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.
Similar content being viewed by others
References
Touretzky, DS, and Pomerleau DA. What’s hidden in the hidden layers? Byte 1989; August issue:227–233.
Fahlman, SE. Faster-learning variations on back-propagation: An empirical study. In Proceedings of the 1988 Connectionist Models Summer School, Morgan Kaufmann, 1988.
Fahlman, SE and Lebieres C. The cascade-correlation learning architecture, In Advances in neural information processing systems 2, Touretzky DS (ed.), Morgan Kaufmann, 1990.
Lang, KJ and Witbrock, MJ. Learning to tell two spirals apart, In Proceedings of the 1988 Connectionist Models Summer School, Morgan Kaufmann, 1988.
Tay, LP and Evans, DJ. Fast learning artificial neural network (FLANN II) using the nearest neighbour recall. Neural, Parallel and Scientific Computations 1994; 2(1): 17–27.
Sun, CT and Jang, JS. A neuro-fuzzy classifier and its applications, In Proceedings of the IEEE International conference on fuzzy systems, 1993, vol. 1, pp. 94–98.
Chua, H, Jia, J, Chen, L and Gong, Y. Solving the two-spiral problem through input data encoding, Electronics letters 1995; 31(10):813–14.
Jia, J and Chua, H. Solving two-spiral problem through input data representation, In Proceedings of the IEEE International conference on neural networks, 1995, vol. 1, pp. 132–135.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1999 Springer-Verlag London Limited
About this paper
Cite this paper
Singh, S. (1999). Neural Learning of Spiral Structures. In: Singh, S. (eds) International Conference on Advances in Pattern Recognition. Springer, London. https://doi.org/10.1007/978-1-4471-0833-7_23
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0833-7_23
Publisher Name: Springer, London
Print ISBN: 978-1-4471-1214-3
Online ISBN: 978-1-4471-0833-7
eBook Packages: Springer Book Archive