论文信息 - On the importance of sorting in "neural gas" training of vector quantizers

On the importance of sorting in "neural gas" training of vector quantizers

The paper considers the role of the sorting process in the well-known "neural gas" model for vector quantization. Theoretical derivations and experimental evidence show that complete sorting is not required for effective training, since limiting the sorted list to even a few top units performs effectively. This property has a significant impact on the implementation of the overall neural model at the local level.

[1] Rodolfo Zunino,et al. Interpolation approaches to vector quantization for image compression , 1996, Neural Networks for Signal Processing VI. Proceedings of the 1996 IEEE Signal Processing Society Workshop.

[2] Thomas Martinetz,et al. 'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[3] Rodolfo Zunino,et al. Hardware Architectures for Vector Quantization in Very Low Bit-Rate Image Coding , 1996 .

[4] Robert M. Gray,et al. An Algorithm for Vector Quantizer Design , 1980, IEEE Trans. Commun..

[5] Bernd Fritzke,et al. A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[6] G. M. Blair. Low cost sorting circuit for VLSI , 1996 .

[7] Belle W. Y. Wei,et al. A VLSI architecture for a real-time code book generator and encoder of a vector quantizer , 1994, IEEE Trans. Very Large Scale Integr. Syst..

[8] Nasser M. Nasrabadi,et al. Image coding using vector quantization: a review , 1988, IEEE Trans. Commun..

[9] Yuguang Fang,et al. Dynamics of a Winner-Take-All Neural Network , 1996, Neural Networks.

[10] I. N. Parker. VLSI architecture , 1986 .