Abstract:We propose a novel nonvolatile threshold adaptive transistor (TAT) for neuromorphic circuits. The threshold adaptive transistor is achieved by embedding a resistive random-access memory (RRAM) material stack between the gate electrode and gate dielectric. During operation, the embedded RRAM device is kept at a high resistance state, which makes it act as a nonvolatile capacitor. The threshold could be nonlinearly adjusted by the voltage pulses applied on the gate of the transistor. We quantitatively estimate the range of the capacitance variation of the RRAM device. The threshold voltage of the TAT is simulated and shows expected variation. The simulated output of an inverter using a TAT shows a nonlinear adaptive behavior.