Implementation of neural gas training in analog VLSI

The design and implementation of a vector quantization neural network is presented. The training algorithm is Neural Gas. The implementation is fully parallel and mainly analog (only control function and long-term memory are digital). A sequential implementation of the required sorting function allows to compute the Neural Gas updating step.

[1]  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..

[2]  Oscal T.-C. Chen,et al.  VLSI systolic binary tree-searched vector quantizer for image compression , 1994, IEEE Trans. Very Large Scale Integr. Syst..

[3]  Rodolfo Zunino,et al.  VLSI architectures for programmable sorting of analog quantities with multiple-chip support , 1997, Proceedings Great Lakes Symposium on VLSI.

[4]  Oscal T.-C. Chen,et al.  A VLSI neural processor for image data compression using self-organization networks , 1992, IEEE Trans. Neural Networks.

[5]  Viktor K. Prasanna,et al.  Modular VLSI architectures for real-time full-search-based vector quantization , 1993, IEEE Trans. Circuits Syst. Video Technol..

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

[7]  John Lazzaro,et al.  Winner-Take-All Networks of O(N) Complexity , 1988, NIPS.

[8]  Rodolfo Zunino,et al.  Mixed analog-digital circuit for linear-time programmable sorting , 1997, Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97.

[9]  Sandro Ridella,et al.  On the importance of sorting in "neural gas" training of vector quantizers , 1997, Proceedings of International Conference on Neural Networks (ICNN'97).

[10]  Rodolfo Zunino,et al.  A vector quantization circuit for trainable neural networks , 1996, Proceedings of Third International Conference on Electronics, Circuits, and Systems.