Files and links (1)
CC BY V4.0, Open Access
Thesis
Deploying Deep Neural Networks with Resource Constraints
Washington State University
Master of Science (MS), Washington State University
01/2022
DOI:
https://doi.org/10.7273/000004429
Handle:
https://hdl.handle.net/2376/124670
Abstract
Deep neural networks (DNNs) have recently gained unprecedented success in various domains. In resource-constrained edge systems (e.g., mobile devices and IoT devices), QoS-aware DNNs are required to meet latency and memory/storage requirements of mission-critical deep learning applications. There is a growing need to deploy deep learning on resource constrained devices. In this thesis, we propose two solutions to this issue: BlinkNet, which is a runtime system that can guarantee both latency and memory/storage bounds for one or multiple DNNs via efficient QoS-aware per-layer approximation. And ParamExplorer, which evaluates hyperparameters of DNNs converted to Spiking Neural Networks (SNNs) and their effect on accuracy in comparison to the original DNN. ParamExplorer evaluates the search space and identifies an optimal hyperparameter configuration to reduce loss of accuracy.
Metrics
3 File views/ downloads
44 Record Views
Details
- Title
- Deploying Deep Neural Networks with Resource Constraints
- Creators
- Theresa VanderWeide
- Contributors
- Xuechen Zhang (Advisor)Xinghui Zhao (Committee Member)Scott Wallace (Committee Member)
- Awarding Institution
- Washington State University
- Academic Unit
- Voiland College of Engineering and Architecture
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University
- Number of pages
- 63
- Identifiers
- 99900883240201842
- Language
- English
- Resource Type
- Thesis