A/D conversion and analog vector quantization using neural network models

A neural network model for an A/D converter shown in the paper is a good example where the computation complexity is reduced when some of the inter-connections and coefficients are removed. The strategy is to use a hierarchical structure which leads to a multi-layer feedforward realization. The analog pipeline connections used in the artificial neural net model for A/D conversion will not be slower in speed than the parallel and recursive structure in the Hopfield model. A set of hyper-planes locates an input pattern in a pattern space. A vector quantizer (VQ) is one type of pattern classifiers. The authors present an analog VQ, where the input is an analog vector and the output is the digital index of the best matching reference vector. The proposed switched-capacitor (SC) realization of the tree-search analog VQ is very practical to be implemented in VLSI