Compact Physical Implementation of Spiking Neural Network Using Ambipolar WSe<sub>2</sub> n-Type/p-Type Ferroelectric Field-Effect Transistor
Jiali Huo, Lingqi Li, Haofei Zheng, Jing Gao, Thaw Tint Te Tun, Heng Xiang, Kah‐Wee Ang
Abstract
Spiking neural networks (SNNs) are attracting increasing interests for their ability to emulate biological processes, offering energy-efficient computation and event-driven processing. Currently, no devices are known to combine both neuronal and synaptic functions. This study presents an experimental demonstration of an ambipolar WSe 2 n-type/p-type ferroelectric field-effect transistor (n/p-FeFET) integrated with ferroelectric Hf 0.5 Zr 0.5 O 2 (HZO) to achieve both volatile and nonvolatile properties in a single device. The nonvolatile n-FeFET, driven by the stable ferroelectric properties of HZO, exhibits highly linear synaptic behavior. In contrast, the volatile p-FeFET, influenced by electron self-compensation in the ambipolar WSe 2, enables self-resetting leaky-integrate-and-fire neurons. Integrating neuronal and synaptic functions in the same device allows for compact neuromorphic computing applications. Additionally, simulations of SNNs using experimentally calibrated synaptic and neuronal models achieved a 93.8% accuracy in MNIST digit recognition. This innovative approach advances the development of SNNs with high biomimetic fidelity and reduced hardware costs.