A four-quadrant floating-gate synapse

We present a new type of pFET synapse; by degenerating the source, the oxide currents provide stabilizing feedback to the floating gate and to the drain. We present experimental measurements from a floating-gate synapse that simultaneously computes four-quadrant products of its input and weight values, and computes a four-quadrant correlation, typical of Hebbian and backpropagation learning rules, between the input and drain voltages. Our four-quadrant synapse is built from two source-degenerated pFET synapses; by adding weak exponential feedback to the source of a floating-gate pFET synapse, we obtain a floating-gate synapse with unique dynamical properties. This four-quadrant synapse can become the fundamental building block of many continuous-time neural-network learning algorithms.