Parallel architectures for vector quantization
F. Ancona, Stefano Rovetta, Rodolfo Zunino · Proceedings of International Conference on Neural Networks (ICNN'97) · 2002
The paper describes a parallel implementation of neural networks based on vector quantization. A toroidal-mesh topology has been used to assess the overall approach. A theoretical analysis of the modular system's efficiency is presented. The final application goal is a lossy compression of high-dimensional data for low bit-rate communications. Experimental results on a significant testbed shows a remarkable increase of the system's performances. In addition, the fit between predicted and measured efficiency values confirms the validity of the overall theoretical model.