The Community for Technology Leaders
Green Image
Issue No. 03 - July-Sept. (2017 vol. 16)
ISSN: 1536-1268
pp: 82-88
Nicholas D. Lane , University College London and Nokia Bell Labs
Sourav Bhattacharya , Nokia Bell Labs
Akhil Mathur , Nokia Bell Labs
Petko Georgiev , Google DeepMind
Claudio Forlivesi , Nokia Bell Labs
Fahim Kawsar , Nokia Bell Labs
This department provides an overview the progress the authors have made to the emerging area of embedded and mobile forms of on-device deep learning. Their work addresses two core technical questions. First, how should deep learning principles and algorithms be applied to sensor inference problems that are central to this class of computing? Second, what is required for current and future deep learning innovations to be efficiently integrated into a variety of mobile resource-constrained systems? Toward answering such questions, the authors describe phone, watch, and embedded prototypes that can locally run large-scale deep networks processing audio, images, and inertial sensor data. These prototypes are enabled with a variety of algorithmic and system-level innovations that vastly reduce conventional inference-time overhead of deep models.
Machine learning, Sensors, Smart phones, Mobile communication, Neural networks, Digital signal processing, Computer architecture, Deep learning, Embedded systems, Smart devices

N. D. Lane, S. Bhattacharya, A. Mathur, P. Georgiev, C. Forlivesi and F. Kawsar, "Squeezing Deep Learning into Mobile and Embedded Devices," in IEEE Pervasive Computing, vol. 16, no. 3, pp. 82-88, 2017.
2766 ms
(Ver 3.3 (11022016))