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...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Lee, Shawn Wei Han
مؤلفون آخرون: Arindam Basu
التنسيق: Final Year Project
اللغة:English
منشور في: Nanyang Technological University 2021
الموضوعات:
الوصول للمادة أونلاين:https://hdl.handle.net/10356/149972
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
الوصف
الملخص: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