Abstract
Mapping of radial basis function network with a hybrid learning method is presented for a partial tree shape neurocomputer. The learning stage is divided into three separate parts, namely K-means clustering, P-nearest neighbor heuristic and weight value determination. The production mode consists of one part. The time complexity is given for each step to illustrate the mapping performance. The analysis shows that radial basis function networks allow efficient parallel implementations.
Preview
Unable to display preview. Download preview PDF.
References
S. Schen, C. Cowan and P. Grant, “Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks”, IEEE Transactions on Neural Networks, Vol. 2, No. 2, pp. 302–309, 1991.
J. Moody and C. Darken, “Fast Learning in Networks of Locally-tuned Processing Units”, Neural Computation, Vol. 1, pp. 281–294,1989.
Current technology Inc., “MM32k Massively Parallel SIMD Processor for Neural Network and Machine Vision Applications”, Durham, USA, 1995.
Nestor Inc., “Ni1000 Recognition Accelerator”, Province, USA, 1995.
IBM Microelectronics, “ZISC036 Data Book (preliminary)”, France, 1994.
T. Hämäläinen, J. Saarinen and K. Kaski, “TUTNC: A General Purpose Parallel Computer for Neural Network Computations”, Microprocessors and Microsystems, Vol. 19, No. 8, 1995, pp. 447–465.
P. Kolinummi, T. Hämäläinen, H. Klapuri and K. Kaski, “Mapping of Multilayer Perceptron Networks to Partial Tree Shape Parallel Neurocomputer”, Lecture Notes in Computer Science, vol 1112, Proceedings of the ICANN'96, Germany, July 1996, pp. 359–364.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kolinummi, P., Hämäläinen, T., Saarinen, J. (1997). Mapping of radial basis function networks to partial tree shape parallel neurocomputer. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020324
Download citation
DOI: https://doi.org/10.1007/BFb0020324
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive