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...

Full description

Saved in:
Bibliographic Details
Main Authors: Piyasena, Duvindu, Lam, Siew-Kei, Wu, Meiqing
Other Authors: College of Computing and Data Science
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