Enabling Deep Learning on IoT Devices

Computer

Volumn 50, Issue 10, 2017, Pages 92-96

  Tang, Jie ^a   Sun, Dawei ^b   Liu, Shaoshan ^c   Gaudiot, Jean Luc ^a  

^a SOUTH CHINA UNIVERSITY OF TECHNOLOGY   (China)

^b TSINGHUA UNIVERSITY   (China)

^c UNIVERSITY OF CALIFORNIA   (United States)

Author keywords

cloud computing; deep learning; embedded devices; Internet of Things; IoT; machine learning; The IoT Connection

Indexed keywords

CLOUD COMPUTING; INTERNET OF THINGS; LEARNING SYSTEMS;

EMBEDDED DEVICE; INTERNET OF THINGS (IOT); IOT DEVICES; LOW POWER; MULTIMEDIA DATA; POWER REQUIREMENT; THE IOT CONNECTION; TWO WAYS;

DEEP LEARNING;

EID: 85031708883     PISSN: 00189162     EISSN: 15580814     Source Type: Trade Journal    
DOI: 10.1109/MC.2017.3641648     Document Type: Article

References (5)

1. J. Tang, Y. Ren, S. Liu, "Real-Time Robot Localization, Vision, Speech Recognition on Nvidia Jetson TX1, " arXiv, 2017; arxiv.org/abs/1705.10945.
2. M. Abadi, et al., "Tensorflow: Largescale Machine Learning on Heterogeneous Distributed Systems, " arXiv, 2016; arxiv.org/abs/1603.04467.
3. F.N. Iandola, et al., "SqueezeNet: Alex-Net-level Accuracy with 50× Fewer Parameters and 0.5 MB Model Size, arXiv 2016; arxiv.org/abs/1602.07360.
4. S. Han, H. Mao, W.J. Dally, "Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding, " arXiv, 2015; arxiv.org/abs/1510.00149.
5. M. Quigley, et al., "ROS: An Open-Source Robot Operating System, " ICRA Workshop Open Source Software, vol. 3, no. 32, 2009; www.willowgarage.com/sites/default/files/icraoss09-ROS.pdf.