TY - GEN
T1 - ALOHA
T2 - 2018 Workshop on INTelligent Embedded Systems Architectures and Applications, INTESA 2018
AU - Meloni, P.
AU - Loi, D.
AU - Deriu, G.
AU - Ripolles, O.
AU - Solans, D.
AU - Pimentel, A. D.
AU - Sapra, D.
AU - Pintor, M.
AU - Biggio, B.
AU - Moser, B.
AU - Shepeleva, N.
AU - Stefanov, T.
AU - Minakova, S.
AU - Conti, F.
AU - Benini, L.
AU - Fragoulis, N.
AU - Theodorakopoulos, I.
AU - Masin, M.
AU - Palumbo, F.
PY - 2018/10/4
Y1 - 2018/10/4
N2 - Novel Deep Learning (DL) algorithms show ever-increasing accuracy and precision in multiple application domains. However, some steps further are needed towards the ubiquitous adoption of this kind of instrument. First, effort and skills required to develop new DL models, or to adapt existing ones to new use-cases, are hardly available for small- and medium-sized businesses. Second, DL inference must be brought at the edge, to overcome limitations posed by the classically-used cloud computing paradigm. This requires implementation on low-energy computing nodes, often heteroge-nous and parallel, that are usually more complex to program and to manage. This work describes the ALOHA framework, that proposes a solution to these issue by means of an integrated tool ow that automates most phases of the development process. The framework introduces architecture-awareness, considering the target inference platform very early, already during algorithm selection, and driving the optimal porting of the resulting embedded application. Moreover it considers security, power eciency and adaptiveness as main objectives during the whole development process.
AB - Novel Deep Learning (DL) algorithms show ever-increasing accuracy and precision in multiple application domains. However, some steps further are needed towards the ubiquitous adoption of this kind of instrument. First, effort and skills required to develop new DL models, or to adapt existing ones to new use-cases, are hardly available for small- and medium-sized businesses. Second, DL inference must be brought at the edge, to overcome limitations posed by the classically-used cloud computing paradigm. This requires implementation on low-energy computing nodes, often heteroge-nous and parallel, that are usually more complex to program and to manage. This work describes the ALOHA framework, that proposes a solution to these issue by means of an integrated tool ow that automates most phases of the development process. The framework introduces architecture-awareness, considering the target inference platform very early, already during algorithm selection, and driving the optimal porting of the resulting embedded application. Moreover it considers security, power eciency and adaptiveness as main objectives during the whole development process.
KW - Computer aided design
KW - Convolutional Neural Networks
KW - Deep Learning
UR - http://www.scopus.com/inward/record.url?scp=85058670162&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85058670162&partnerID=8YFLogxK
U2 - 10.1145/3285017.3285019
DO - 10.1145/3285017.3285019
M3 - Conference contribution
AN - SCOPUS:85058670162
T3 - ACM International Conference Proceeding Series
SP - 19
EP - 26
BT - Workshop Proceedings - 2018 INTelligent Embedded Systems Architectures and Applications, INTESA 2018
PB - Association for Computing Machinery
Y2 - 4 October 2018
ER -