Edge accelerator for lifelong deep learning using streaming linear discriminant analysis
Lifelong deep learning models are expected to continuously adapt and acquire new knowledge in dynamic environments. This capability is essential for numerous vision tasks in robotics and drones, and the models must be deployed on the edge to achieve real-time performance. We propose a FPGA accelerat...
Saved in:
Main Authors: | , , |
---|---|
Other Authors: | |
Format: | Conference or Workshop Item |
Language: | English |
Published: |
2024
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/178585 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-178585 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1785852024-06-27T01:03:51Z Edge accelerator for lifelong deep learning using streaming linear discriminant analysis Piyasena, Duvindu Lam, Siew-Kei Wu, Meiqing College of Computing and Data Science School of Computer Science and Engineering 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM) Computer and Information Science FPGA Deep learning Lifelong deep learning models are expected to continuously adapt and acquire new knowledge in dynamic environments. This capability is essential for numerous vision tasks in robotics and drones, and the models must be deployed on the edge to achieve real-time performance. We propose a FPGA accelerator of a streaming classifier for lifelong deep learning, which is based on streaming linear discriminant analysis (SLDA). When combined with a frozen Convolutional Neural Network (CNN) model, the proposed system is capable of class incremental lifelong learning for object classification. 2024-06-27T01:03:51Z 2024-06-27T01:03:51Z 2021 Conference Paper Piyasena, D., Lam, S. & Wu, M. (2021). Edge accelerator for lifelong deep learning using streaming linear discriminant analysis. 2021 IEEE 29th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), 259-259. https://dx.doi.org/10.1109/FCCM51124.2021.00046 978-1-6654-3555-0 https://hdl.handle.net/10356/178585 10.1109/FCCM51124.2021.00046 2-s2.0-85107664245 259 259 en © 2021 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Computer and Information Science FPGA Deep learning |
spellingShingle |
Computer and Information Science FPGA Deep learning Piyasena, Duvindu Lam, Siew-Kei Wu, Meiqing Edge accelerator for lifelong deep learning using streaming linear discriminant analysis |
description |
Lifelong deep learning models are expected to continuously adapt and acquire new knowledge in dynamic environments. This capability is essential for numerous vision tasks in robotics and drones, and the models must be deployed on the edge to achieve real-time performance. We propose a FPGA accelerator of a streaming classifier for lifelong deep learning, which is based on streaming linear discriminant analysis (SLDA). When combined with a frozen Convolutional Neural Network (CNN) model, the proposed system is capable of class incremental lifelong learning for object classification. |
author2 |
College of Computing and Data Science |
author_facet |
College of Computing and Data Science Piyasena, Duvindu Lam, Siew-Kei Wu, Meiqing |
format |
Conference or Workshop Item |
author |
Piyasena, Duvindu Lam, Siew-Kei Wu, Meiqing |
author_sort |
Piyasena, Duvindu |
title |
Edge accelerator for lifelong deep learning using streaming linear discriminant analysis |
title_short |
Edge accelerator for lifelong deep learning using streaming linear discriminant analysis |
title_full |
Edge accelerator for lifelong deep learning using streaming linear discriminant analysis |
title_fullStr |
Edge accelerator for lifelong deep learning using streaming linear discriminant analysis |
title_full_unstemmed |
Edge accelerator for lifelong deep learning using streaming linear discriminant analysis |
title_sort |
edge accelerator for lifelong deep learning using streaming linear discriminant analysis |
publishDate |
2024 |
url |
https://hdl.handle.net/10356/178585 |
_version_ |
1806059831385128960 |