Pr. Chang et al., A TRIANGULAR CONNECTION HOPFIELD NEURAL-NETWORK APPROACH TO ANALOG-TO-DIGITAL CONVERSION, IEEE transactions on instrumentation and measurement, 43(6), 1994, pp. 882-888
A Hopfield-type neural network approach which leads to an analog circu
it for implementing the A/D conversion is presented. The solution of t
he original symmetric connection Hopfield A/D converter sometimes may
reach a ''spurious state'' that does not correspond to the correct dig
ital representation of the input signal. An A/D converter based on the
model of nonsymmetrical neural networks is proposed to obtain the sta
ble and correct encoding. Due to the infeasible conventional RC-active
implementation, a cost-effective switched-capacitor implementation by
means of Schmitt triggers is adopted. It is capable of achieving high
performance as well as a high convergence rate. Finally, a simulation
using a tool called SWITCAP is conducted to verify the validity and p
erformance of the proposed implementation.