Abstract
In recent advancement of technology implementing Machine Learning (ML) algorithms with edge devices has gained remarkable popularity. Enabling Machine Learning (ML) in the edge opened new hybrid branch where edge hardware meets with Machine Learning (ML). Day by day devices are becoming more powerful and capable of doing a lot of computation. These powerful computational capabilities created the way of implementing Machine Learning (ML) on small edge devices. There are diverse ways we can implement machine learning models to the edge. For any embedded prototype, implementation of Tiny Machine Learning (TinyML) is making the IoT (Internet of Things) devices intelligent and reducing unnecessary communications. the This thesis paper explores the practical implementation of various embedded prototypes and on-device learning, focusing on Field Programmable Gate Arrays (FPGA), microcontrollers and single board computers (Raspberry Pi, Jetson Nano etc.).
Date of publication
Spring 5-4-2024
Document Type
Thesis
Language
english
Persistent identifier
http://hdl.handle.net/10950/4700
Committee members
Thesis Chair: Dr. Prabha Sundaravadivel, Ph.D, Member: Dr. Premananda Indic, Ph.D, Member: Dr. Aaditya Khanal, Ph.D
Degree
MS ELECTRICAL ENGINEERING
Recommended Citation
Ahmed, Md Sharif, "ENABLING ON-DEVICE LEARNING THROUGH HYBRID EDGE COMPUTING FRAMEWORKS" (2024). Electrical Engineering Theses. Paper 58.
http://hdl.handle.net/10950/4700