Artificial Intelligence on Edge-FPGA Based Neural Network Inference

dc.contributor.author	Esha Noor, 01-133202-033
dc.contributor.author	Qaisar Zia, 01-133202-167
dc.contributor.author	Awais khan, 01-133202-162
dc.date.accessioned	2024-07-25T06:24:08Z
dc.date.available	2024-07-25T06:24:08Z
dc.date.issued	2024
dc.identifier.uri	http://hdl.handle.net/123456789/17580
dc.description	Supervised by Engr. Adnan Yaqoob	en_US
dc.description.abstract	The project aims to make object detection smarter and more efficient. Our main focus is reducing the need for resources to improve object detection and ensure it works quickly. This time a new approach called quantization neural network (QNN) and the system will run on hardware called a MiniZed board (FPGA board). By using FPGA, a fast system process will be ensured. The system will be tested in real-life situations making sure it can adapt to diﬀerent needs	en_US
dc.language.iso	en	en_US
dc.publisher	Electrical Engineering, Bahria University Engineering School Islamabad	en_US
dc.relation.ispartofseries	BEE;P-2747
dc.subject	Electrical Engineering	en_US
dc.subject	Implementation of YOLO on FPGA	en_US
dc.subject	The Goals Achieved	en_US
dc.title	Artificial Intelligence on Edge-FPGA Based Neural Network Inference	en_US
dc.type	Project Reports	en_US