Optimization and deployment of CNNs at the Edge: The ALOHA experience

Paolo Meloni, Daniela Loi, Paola Busia, Gianfranco Deriu, Andy D. Pimentel, Dolly Sapra, Todor Stefanov, Svetlana Minakova, Francesco Conti, Luca Benini, Maura Pintor, Battista Biggio, Bernhard Moser, Natalia Shepelev, Nikos Fragoulis, Ilias Theodorakopoulos, Michael Masin, Francesca Palumbo

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Deep learning (DL) algorithms have already proved their effectiveness on a wide variety of application domains, including speech recognition, natural language processing, and image classification. To foster their pervasive adoption in applications where low latency, privacy issues and data bandwidth are paramount, the current trend is to perform inference tasks at the edge. This requires deployment of DL algorithms on low-energy and resource-constrained computing nodes, often heterogenous and parallel, that are usually more complex to program and to manage without adequate support and experience. In this paper, we present ALOHA, an integrated tool flow that tries to facilitate the design of DL applications and their porting on embedded heterogenous architectures. The proposed tool flow aims at automating different design steps and reducing development costs. ALOHA considers hardware-related variables and security, power efficiency, and adaptivity aspects during the whole development process, from pre-training hyperparameter optimization and algorithm configuration to deployment.

Original languageEnglish
Title of host publicationACM International Conference on Computing Frontiers 2019, CF 2019 - Proceedings
PublisherAssociation for Computing Machinery, Inc
Pages326-332
Number of pages7
ISBN (Electronic)9781450366854
DOIs
Publication statusPublished - 30 Apr 2019
Externally publishedYes
Event16th ACM International Conference on Computing Frontiers, CF 2019 - Alghero, Sardinia, Italy
Duration: 30 Apr 20192 May 2019

Publication series

NameACM International Conference on Computing Frontiers 2019, CF 2019 - Proceedings

Conference

Conference16th ACM International Conference on Computing Frontiers, CF 2019
Country/TerritoryItaly
CityAlghero, Sardinia
Period30/04/192/05/19

Keywords

  • Convolution Neural Networks
  • FPGAs
  • Hardware accelerators

Fingerprint

Dive into the research topics of 'Optimization and deployment of CNNs at the Edge: The ALOHA experience'. Together they form a unique fingerprint.

Cite this