A comparison of two neural network architectures for vector quantization
Mort Naraghi‐Pour, M.V. Hedge, F. Bourge · 2002
The authors investigate the performance of two neural network architectures for vector quantization. The two architectures are the multilayer feedforward network and the Hopfield analog neural network. If is found that for the feedforward network to have reasonably good performance, the number of hidden units must be unrealistically high: exponential in the number of dimensions and codewords. For the Hopfield analog model, on the other hand, the number of processors required is equal to the number of codewords and the resulting performance is very close to the optimum mean squared error.>