Temperature compensation for analog machine learners (II)
The widespread adoption of the Internet of Things (IoT) in everyday life has increased demand for ever-increasing computational resources in cloud computing. The use of analogue processing and the extreme machine learning (ELM) algorithm in the design of ultra-low power machine learners for "sm...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Final Year Project |
| 語言: | English |
| 出版: |
Nanyang Technological University
2021
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/149972 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | The widespread adoption of the Internet of Things (IoT) in everyday life has increased demand for ever-increasing computational resources in cloud computing. The use of analogue processing and the extreme machine learning (ELM) algorithm in the design of ultra-low power machine learners for "smart" sensors has proven to be beneficial. However, due to sub-threshold transistor operation, the reliance of these systems' weights on temperature cannot be overlooked. The aim of this project is to use behavioral simulations to determine the best form of temperature behavior for current reference in this framework. State-of-the-art IC modeling software and CMOS processes will be used to design and simulate the corresponding circuits |
|---|