Flex: Fast, Accurate DNN Inference on Low-Cost Edges Using Heterogeneous Accelerator Execution
Open Access
- 30 March 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 507-523
Abstract
No abstract availableFunding Information
- NSF (National Science Foundation) (2206522, 2319988)
- Commonwealth Cyber Initiative (CCI)
- Microsoft Research Faculty Fellowship (8300751)
- FHWA (693JJ31950016)
This publication has 26 references indexed in Scilit:
- Depression detection using emotional artificial intelligence and machine learning: A closer reviewMaterials Today: Proceedings, 2022
- Enabling Inference and Training of Deep Learning Models for AI Applications on IoT Edge Devices2022
- Benchmarking Vulkan vs OpenGL Rendering on Low-Power Edge GPUs2021
- Applications of smart technologies in logistics and transport: A reviewTransportation Research Part E: Logistics and Transportation Review, 2021
- Edge Intelligence for Autonomous Driving in 6G Wireless System: Design Challenges and SolutionsIEEE Wireless Communications, 2021
- Performance Dynamics and Termination Errors in Reinforcement Learning – A Unifying Perspective2018
- S^3DNN: Supervised Streaming and Scheduling for GPU-Accelerated Real-Time DNN Workloads2018
- ImageNet: A large-scale hierarchical image database2009
- Random ForestsMachine Learning, 2001
- Kolmogorov-Smirnov Test for Two-Dimensional DataComputers in Physics, 1988