| المؤلفون: |
Li L; Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583. eleakw@nus.edu.sg., Xiang H; Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583. eleakw@nus.edu.sg., Zheng H; Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583. eleakw@nus.edu.sg., Chien YC; Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583. eleakw@nus.edu.sg., Duong NT; Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583. eleakw@nus.edu.sg., Gao J; Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583. eleakw@nus.edu.sg., Ang KW; Department of Electrical and Computer Engineering, National University of Singapore, 4 Engineering Drive 3, Singapore, 117583. eleakw@nus.edu.sg. |
| مستخلص: |
Reservoir computing (RC), a variant of recurrent neural networks (RNNs), is well-known for its reduced energy consumption through exclusive focus on training the output weight and its superior performance in handling spatiotemporal information. Implementing these networks in hardware requires devices with superior fading memory behavior. Unlike filament-based two-terminal devices, those relying on ferroelectric switching demonstrate improved voltage reliability, while three-terminal transistors provide additional active control. HfO 2 -based ferroelectric materials such as Hf 0.5 Zr 0.5 O 2 (HZO), have garnered attention for their scalability and seamless integration with CMOS technology. This study implements a RC hardware based on MoS 2 -HZO integrated device structure with enhanced spontaneous polarization field. By adjusting the oxygen vacancy concentration, the devices exhibit consistent responses to both identical and nonidentical voltages, making them suitable for diverse RC applications. The high accuracy of MNIST handwritten digits recognition highlights the rich reservoir states of the traditional RC architecture. Additionally, the impact of masks on RC implementation is assessed, showcasing the device's capability for spatiotemporal signal analysis. This development paves the way for implementing energy-efficient and high-performance computing solutions. |
