| 神经网络矢量量化的设计与实现 |
| |
| 引用本文： | 徐勇,戴逸松,陈贺新. 神经网络矢量量化的设计与实现[J]. 吉林大学学报(信息科学版), 1996, 0(3) |
| |
| 作者姓名： | 徐勇 戴逸松 陈贺新 |
| |
| 作者单位： | 长春邮电学院科技处，吉林工业大学电子工程系 |
| |
| 摘 要： | 设计了一种混合神经网络矢量量化编码方法。利用Ｋｏｈｏｎｅｎ网络的自组织聚类功能设计矢量量化器码书，实现矢量量化，用３层ＢＰ网络完成码字的信道符号编码。该神经网络矢量量化编码器能够并行处理输入矢量，速度快，效率高，适用于语音和图像数据压缩
|
| 关 键 词： | 神经网络；数据压缩；矢量量化 |
Design and implementation of vector quantization based upon a hybrid neural network |
| |
| Xu Yong,Dai Yisong,Chen Hexin. Design and implementation of vector quantization based upon a hybrid neural network[J]. Journal of Jilin University:Information Sci Ed, 1996, 0(3) |
| |
| Authors: | Xu Yong Dai Yisong Chen Hexin |
| |
| Abstract: | A coding scheme for vector quantization is presented by using a hybrid neural network. The clustering function of the Kohonen self organizing feature map is used to design codebook of vector quantizer and to carry out vector quantization, then the channel index for codeword is made by a three layers BP (Back Propagation) network. Processing input vectors in parallel mode fast and effectively, the vector quantization coder based upon neural networks is sutable for voice and image data compression. |
| |
| Keywords: | Neural network Data compression Vector quantization |
| 本文献已被 CNKI 等数据库收录！ |
