Significant effort for demonstrating a gallium nitride
(GaN)-based
ferroelectric metal–oxide–semiconductor (MOS)-high-electron-mobility
transistor (HEMT) for reconfigurable operation via simple pulse operation
has been hindered by the lack of suitable materials, gate structures,
and intrinsic depolarization effects. In this study, we have demonstrated
artificial synapses using a GaN-based MOS-HEMT integrated with an α-In2Se3 ferroelectric semiconductor. The van der Waals heterostructure
of GaN/α-In2Se3 provides a potential to
achieve high-frequency operation driven by a ferroelectrically coupled
two-dimensional electron gas (2DEG). Moreover, the semiconducting
α-In2Se3 features a steep subthreshold
slope with a high ON/OFF ratio (∼1010). The self-aligned
α-In2Se3 layer with the gate electrode
suppresses the in-plane polarization while promoting the out-of-plane
(OOP) polarization of α-In2Se3, resulting
in a steep subthreshold slope (10 mV/dec) and creating a large hysteresis
(2 V). Furthermore, based on the short-term plasticity (STP) characteristics
of the fabricated ferroelectric HEMT, we demonstrated reservoir computing
(RC) for image classification. We believe that the ferroelectric GaN/α-In2Se3 HEMT can provide a viable pathway toward ultrafast
neuromorphic computing.