Abstract
In this paper a special higher order neuron, the hypersphere neuron, is introduced. By embedding Euclidean space in a conformal space, hyperspheres can be expressed as vectors. The scalar product of points and spheres in conformal space, gives a measure for how far a point lies inside or outside a hypersphere. It will be shown that a hypersphere neuron may be implemented as a perceptron with two bias inputs. By using hyperspheres instead of hyperplanes as decision surfaces, a reduction in computational complexity can be achieved for certain types of problems. This is shown in two experiments using classical test data for neural computing. Furthermore, in this setup, a reliability measure can be associated with data points in a straight forward way.
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
Abu-Mostafa, Y.S.: The Vapnik-Chervonenkis dimension: Information versus complexity in learning. Neural Computation 1(3), 312–317 (1989)
Buchholz, S., Sommer, G.: A hyperbolic multilayer perceptron. In: Amari, S.-I., Giles, C.L., Gori, M., Piuri, V. (eds.) International Joint Conference on Neural Networks, IJCNN 2000, Como, Italy, vol. 2, pp. 129–133. IEEE Computer Society Press, Los Alamitos (2000)
Cybenko, G.: Approximation by superposition of a sigmoidal function. Mathematics of Control, Signals and Systems 2, 303–314 (1989)
Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, Denver 1989, vol. 2, pp. 524–532. Morgan Kaufmann, San Mateo (1990)
Fisher, R.A.: The use of multiple measurements in axonomic problems. Annals of Eugenics 7, 179–188 (1936)
Hornik, K.: Approximation capabilities of multilayer feedforward neural networks. Neural Networks 4, 251–257 (1990)
Hoyle, L.: http://www.ku.edu/cwis/units/IPPBR/java/iris/irisglyph.html
Lang, K.J., Witbrock, M.J.: Learning to tell two spirals apart. In: Touretzky, D.S., Hinton, G.E., Sejnowski, T. (eds.) Connectionist Models Summer School. Morgan Kaufmann, San Francisco (1988)
Li, H., Hestenes, D., Rockwood, A.: Generalized homogeneous coordinates for computational geometry. In: Sommer, G. (ed.) Geometric Computing with Clifford Algebra, pp. 27–52. Springer, Heidelberg (2001)
Li, H., Hestenes, D., Rockwood, A.: A universal model for conformal geometries. In: Sommer, G. (ed.) Geometric Computing with Clifford Algebra, pp. 77–118. Springer, Heidelberg (2001)
Lipson, H., Siegelmann, H.T.: Clustering irregular shapes using high-order neurons. Neural Computation 12(10), 2331–2353 (2000)
Minsky, M., Papert, S.: Perceptrons. MIT Press, Cambridge (1969)
Ritter, H.: Self-organising maps in non-Euclidean spaces. In: Oja, E., Kaski, S. (eds.) Kohonen Maps, pp. 97–108. Amer Elsevier, Amsterdam (1999)
Wieland, A., Fahlman, S.E.: http://www.ibiblio.org/pub/academic/computer-science/neural-networks/programs/bench/two-spirals (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Banarer, V., Perwass, C., Sommer, G. (2003). Design of a Multilayered Feed-Forward Neural Network Using Hypersphere Neurons. In: Petkov, N., Westenberg, M.A. (eds) Computer Analysis of Images and Patterns. CAIP 2003. Lecture Notes in Computer Science, vol 2756. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45179-2_70
Download citation
DOI: https://doi.org/10.1007/978-3-540-45179-2_70
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40730-0
Online ISBN: 978-3-540-45179-2
eBook Packages: Springer Book Archive