Write a Blog >>
LCTES 2018
co-located with PLDI 2018

The recent ground-breaking advances in deep learning networks (DNNs) make them attractive for embedded systems. However, it can take a long time for DNNs to make an inference on resource-limited embedded devices. Offloading the computation into the cloud is often infeasible due to privacy concerns, high latency, or the lack of connectivity. As such, there is a critical need to find a way to effectively execute the DNN models locally on the devices. This paper presents an adaptive scheme to determine which DNN model to use for a given input, by considering the desired accuracy and inference time. Our approach employs machine learning to develop a predictive model to quickly select a pre-trained DNN to use for a given input and the optimization constraint. We achieve this by first training off-line a predictive model, and then use the learnt model to select a DNN model to use for new, unseen inputs. We apply our approach to the image classification task and evaluate it on a Jetson TX2 embedded deep learning platform using the ImageNet ILSVRC 2012 validation dataset. We consider a range of influential DNN models. Experimental results show that our approach achieves a 7.52% improvement in inference accuracy, and a 1.8x reduction in inference time over the most-capable single DNN model.

Conference Day
Tue 19 Jun

Displayed time zone: Eastern Time (US & Canada) change

14:00 - 15:40
Full paper session on Adaptation and HardwareLCTES 2018 at Discovery AB
14:00
25m
Full-paper
Adaptive Deep Learning Model Selection on Embedded Systems
LCTES 2018
Ben TaylorLancaster University, UK, Vicent Sanz MarcoLancaster University, Willy WolffLancaster University, Yehia ElkhatibLancaster University, Zheng WangLancaster University
14:25
25m
Full-paper
Optimizing RAID/SSD Controllers with Lifetime Extension for Flash-based SSD Array
LCTES 2018
Lei Han, Zhaoyan ShenThe Hong Kong Polytechnic University, Zili ShaoThe Hong Kong Polytechnic University, Tao LiUniversity of Florida
14:50
25m
Full-paper
Verification of Coarse-Grained Reconfigurable Arrays through Random Test Programs
LCTES 2018
Bernhard EggerSeoul National University, Eunjin SongSeoul National University, Hochan LeeSeoul National University, Daeyoung ShinSeoul National University
15:15
25m
Full-paper
Decoupling Address Generation from Loads and Stores to Improve Data Access Energy Efficiency
LCTES 2018
Michael StokesFlorida State University, Ryan BairdFlorida State University, Zhaoxiang JinMichigan Technological University, David B. Whalley, Soner OnderMichigan Technological University