A self-deleting neural network for vector quantization

Vector quantization is required the algorithm that minimizes the distortion error, and used for both storage and transmission of speech and image data. For a neural vector quantization [1], the self-creating neural network [2] and self-deleting neural network [3] and known for showing fine characters. In this paper, we improve the self-deleting neural network, and propose a generalization algorithm combining the creating and deleting neural networks. We discuss algorithms with neighborhood relations [2]similar to[5] compared with the proposed one. Experimental results show the effectiveness of the proposed algorithm.