Design and implementation of a calibrating T-model neural-based A/D converter

A calibrating analog-to-digital (A/D) converter employing a T-Model neural network is described. The T-Model neural-based A/D converter architecture is presented with particular emphasis on the elimination of local minimum of the Hopfield neural network. Furthermore, a teacher forcing algorithm is presented and used to synthesize the A/D converter and correct errors of the converter due to offset and device mismatch. An experimental A/D converter using standard 5-mu m CMOS discrete IC circuits demonstrates high-performance analog-to-digital conversion and calibrating.