TY - GEN
T1 - An overview of next-generation architectures for machine learning
T2 - 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018
AU - Shafique, Muhammad
AU - Theocharides, Theocharis
AU - Bouganis, Christos Savvas
AU - Hanif, Muhammad Abdullah
AU - Khalid, Faiq
AU - Hafiz, Rehan
AU - Rehman, Semeen
N1 - Publisher Copyright:
© 2018 EDAA.
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2018/4/19
Y1 - 2018/4/19
N2 - The number of connected Internet of Things (IoT) devices are expected to reach over 20 billion by 2020. These range from basic sensor nodes that log and report the data to the ones that are capable of processing the incoming information and taking an action accordingly. Machine learning, and in particular deep learning, is the de facto processing paradigm for intelligently processing these immense volumes of data. However, the resource inhibited environment of IoT devices, owing to their limited energy budget and low compute capabilities, render them a challenging platform for deployment of desired data analytics. This paper provides an overview of the current and emerging trends in designing highly efficient, reliable, secure and scalable machine learning architectures for such devices. The paper highlights the focal challenges and obstacles being faced by the community in achieving its desired goals. The paper further presents a roadmap that can help in addressing the highlighted challenges and thereby designing scalable, high-performance, and energy efficient architectures for performing machine learning on the edge.
AB - The number of connected Internet of Things (IoT) devices are expected to reach over 20 billion by 2020. These range from basic sensor nodes that log and report the data to the ones that are capable of processing the incoming information and taking an action accordingly. Machine learning, and in particular deep learning, is the de facto processing paradigm for intelligently processing these immense volumes of data. However, the resource inhibited environment of IoT devices, owing to their limited energy budget and low compute capabilities, render them a challenging platform for deployment of desired data analytics. This paper provides an overview of the current and emerging trends in designing highly efficient, reliable, secure and scalable machine learning architectures for such devices. The paper highlights the focal challenges and obstacles being faced by the community in achieving its desired goals. The paper further presents a roadmap that can help in addressing the highlighted challenges and thereby designing scalable, high-performance, and energy efficient architectures for performing machine learning on the edge.
KW - Convolutional Neural Networks
KW - Deep Learning
KW - IoT
KW - Machine Learning
UR - http://www.scopus.com/inward/record.url?scp=85048785359&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048785359&partnerID=8YFLogxK
U2 - 10.23919/DATE.2018.8342120
DO - 10.23919/DATE.2018.8342120
M3 - Conference contribution
AN - SCOPUS:85048785359
T3 - Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018
SP - 827
EP - 832
BT - Proceedings of the 2018 Design, Automation and Test in Europe Conference and Exhibition, DATE 2018
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 19 March 2018 through 23 March 2018
ER -