Stability in a class of resistive grid networks containing active device realizations of nonlinear resistors

In the analog VLSI implementation of neural systems, it is sometimes convenient to build networks by using a locally connected on-chip resistive grid. A problem of unwanted spontaneous oscillation often arises with these circuits and renders them unusable in practice. Recent work on design criteria for such networks considers the stability of a circuit class consisting of nonlinear resistors, nonlinear capacitors, and linear driving-point impedances, all of which are two-terminal elements. This study, which is an extension of earlier work, allows a more general dynamic element to be included in the network. The new element class allows modeling of the dynamics of nonlinear resistors realized with transistors; this is useful where memoryless I-V characteristic modeling is not appropriate. The extended criteria are local in the sense that no global analysis of the network is needed, and robust in the sense that unmodeled parasitic resistance and capacitance in the resistive grid do not affect the stability result