Normalization of input vector is essential for a competitive learning neural network using the inner product. In this paper we propose a transformation method of input vector without losing the norm information. To conserve the norm information, an additional vector component concerning the norm is introduced besides the original normalized components of the input vector. By applying the method to Kohonen’s self-organizing feature map, its usefulness is demonstrated. We also propose an optical apparatus for its realization.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
T. Lu, F.T.S. Yu and D.A. Gregory: Opt. Eng. 29 (1990).
J. Duivillier, M. Killinger, K. Heggarty, K. Yao and J.L. de Bougrenet de la Tocnaye: Appl. Opt. 33 (1994).
M. Terashima, F. Shiratani and K. Yamamoto:Proceedings of JNNS’ 94, (1994) p. 221.
T. Kohonen:Self-Organization and Associative Memory, (Springer-Verlag, Berlin, 1989) 3rd ed.
About this article
Cite this article
Terashima, M., Shiratani, F., Hashimoto, T. et al. A normalization method of input data that conserves the norm information for competitive learning neural network using inner product. Optical Review 3, A414–A417 (1996). https://doi.org/10.1007/BF02935947
- normalization method
- competitive learning neural network
- inner product