Abstract | ||
---|---|---|
The biology-inspired intelligent computing system for the neuromorphic hardware implementation is useful in high-speed parallel information processing. However, the traditional Von Neumann computer architecture and the unsatisfactory signal transmission approach have jointly limited the overall performance of the specific hardware implementation. In this paper, a compact extreme learning machine (ELM) architecture synthesized with the spintronic memristor-based synaptic circuit, the biasing circuit, and the activation function circuit is presented. Notably, due to the threshold characteristic of the memristive device, the synaptic circuit has a bimodal behavior. Namely, it is capable to provide the constant and adjustable network weights between the adjacent layers in the ELM. Furthermore, two major limitations (process variations and sneak path issue) are taken into account for the detailed robustness analysis of the whole network. Finally, the entire scheme is verified with case studies in single image super-resolution (SR) reconstruction. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1016/j.neucom.2021.04.049 | Neurocomputing |
Keywords | DocType | Volume |
Bimodal behavior,Extreme learning machine,Image super-resolution,Neuromorphic hardware implementation | Journal | 453 |
ISSN | Citations | PageRank |
0925-2312 | 1 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhekang Dong | 1 | 2 | 1.72 |
Chun Sing Lai | 2 | 41 | 15.62 |
Zhaowei Zhang | 3 | 1 | 0.34 |
Yi Zheng | 4 | 14 | 2.63 |
Mingyu Gao | 5 | 1 | 0.34 |
Shukai Duan | 6 | 13 | 5.62 |