Publication Type

Conference Proceeding Article

Publication Date

6-2016

Abstract

Recently, a branch of machine learning algorithms called deep learning gained huge attention to boost up accuracy of a variety of sensing applications. However, execution of deep learning algorithm such as convolutional neural network on mobile processor is non-trivial due to intensive computational requirements. In this paper, we present our early design of DeepSense - a mobile GPU-based deep convolutional neural network (CNN) framework. For its design, we first explored the differences between server-class and mobile-class GPUs, and studied effectiveness of various optimization strategies such as branch divergence elimination and memory vectorization. Our results show that DeepSense is able to execute a variety of CNN models for image recognition, object detection and face recognition in soft real time with no or marginal accuracy tradeoffs. Experiments also show that our framework is scalable across multiple devices with different GPU architectures (e.g. Adreno and Mali).

Keywords

Deep learning, Mobile GPU, Mobile sensing application

Discipline

Computer Sciences | Software Engineering

Research Areas

Software and Cyber-Physical Systems

Publication

WearSys'16: Proceedings of the 2016 Workshop on Wearable Systems and Applications: June 30, 2016, Singapore

First Page

25

Last Page

30

ISBN

9781450343268

Identifier

10.1145/2935643.2935650

Publisher

ACM

City or Country

New York

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Additional URL

http://doi.org/10.1145/2935643.2935650

Share

COinS