[OPTICAL REVIEW Vol. 3, No. 6A (1996) 414-417]
A Normalization Method of Input Data That Conserves the Norm Information for Competitive Learning Neural Network Using Inner Product
Mikihiko TERASHIMA, Fumiyuki SHIRATANI, Takeshi HASHIMOTO and Kimiaki YAMAMOTO
Optical Research Laboratory, Olympus Optical Co., Ltd., 2-3, Kuboyama-cho, Hachioji-shi, Tokyo, 192 Japan
(Received May 9, 1996; Accepted July 3, 1996)
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.
Key words : normalization method, competitive learning neural network, inner product, L1-norm, L2-norm, SOM