UCL Discovery Stage
UCL home » Library Services » Electronic resources » UCL Discovery Stage

Sparsifying Deep Learning Layers for Constrained Resource Inference on Wearables

Lane, N; Bhattacharya, S; (2016) Sparsifying Deep Learning Layers for Constrained Resource Inference on Wearables. In: Proceedings of the 14th ACM Conference on Embedded Network Sensor Systems. (pp. pp. 176-189). ACM: Stanford, CA, USA. Green open access

[thumbnail of main (3).pdf]
Preview
Text
main (3).pdf - Accepted Version

Download (4MB) | Preview

Abstract

Deep learning has revolutionized the way sensor data are analyzed and interpreted. The accuracy gains these approaches offer make them attractive for the next generation of mobile, wearable and embedded sensory applications. However, state-of-the-art deep learning algorithms typically require a significant amount of device and processor resources, even just for the inference stages that are used to discriminate high-level classes from low-level data. The limited availability of memory, computation, and energy on mobile and embedded platforms thus pose a significant challenge to the adoption of these powerful learning techniques. In this paper, we propose SparseSep, a new approach that leverages the sparsification of fully connected layers and separation of convolutional kernels to reduce the resource requirements of popular deep learning algorithms. As a result, SparseSep allows large-scale DNNs and CNNs to run efficiently on mobile and embedded hardware with only minimal impact on inference accuracy. We experiment using SparseSep across a variety of common processors such as the Qualcomm Snapdragon 400, ARM Cortex M0 and M3, and Nvidia Tegra K1, and show that it allows inference for various deep models to execute more efficiently; for example, on average requiring 11.3 times less memory and running 13.3 times faster on these representative platforms.

Type: Proceedings paper
Title: Sparsifying Deep Learning Layers for Constrained Resource Inference on Wearables
Event: SenSys 2016 14th ACM Conference on Embedded Networked Sensor Systems (SenSys 2016)
Location: Stanford, CA
Dates: 14 November 2016 - 16 November 2016
ISBN-13: 978-1-4503-4263-6
Open access status: An open access version is available from UCL Discovery
DOI: 10.1145/2994551.2994564
Publisher version: https://doi.org/10.1145/2994551.2994564
Language: English
Additional information: © ACM, 2016. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in: Proceedings of the 14th ACM Conference on Embedded Network Sensor Systems CD-ROM, http://dx.doi.org/10.1145/2994551.2994564
Keywords: Wearable computing; deep learning; sparse coding; weight factorization
UCL classification: UCL
UCL > Provost and Vice Provost Offices > UCL BEAMS
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science
UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science
URI: https://discovery-pp.ucl.ac.uk/id/eprint/1535346
Downloads since deposit
26,604Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item