Bonseyes AI pipeline : bringing AI to you

De Prado, Miguel (School of Engineering – HE-Arc Ingénierie, HES-SO // University of Applied Sciences Western Switzerland ; Integrated Systems Lab, ETH Zurich, Zurich, Switzerland) ; Su, Jing (School of Computer Science & Statistics, Trinity College Dublin, Dublin, Ireland) ; Saeed, Rabia (School of Engineering – HE-Arc Ingénierie, HES-SO // University of Applied Sciences Western Switzerland) ; Keller, Lorenzo (Nviso, Switzerland) ; Vallez, Noelia (Universidad de Castilla, La Mancha, Spain) ; Anderson, Andrew (School of Computer & Statistics, Trinity College Dublin, Dublin, Ireland) ; Gregg, David (School of Computer & Statistics, Trinity College Dublin, Dublin, Ireland) ; Benini, Luca (Integrated Systems Lab, ETH Zurich, Zurich, Switzerland) ; Llewellynn, Tim (Nviso, Switzerland) ; Ouerhani, Nabil (School of Engineering – HE-Arc Ingénierie, HES-SO // University of Applied Sciences Western Switzerland) ; Dahyot, Rozenn (School of Computer Science & Statistics, Trinity College Dublin, Dublin, Ireland) ; Pazos Escudero, Nuria (School of Engineering – HE-Arc Ingénierie, HES-SO // University of Applied Sciences Western Switzerland)

Next generation of embedded Information and Communication Technology (ICT) systems are interconnected and collaborative systems able to perform autonomous tasks. The remarkable expansion of the embedded ICT market, together with the rise and breakthroughs of Artificial Intelligence (AI), have put the focus on the Edge as it stands as one of the keys for the next technological revolution: the seamless integration of AI in our daily life. However, training and deployment of custom AI solutions on embedded devices require a fine-grained integration of data, algorithms, and tools to achieve high accuracy and overcome functional and non-functional requirements. Such integration requires a high level of expertise that becomes a real bottleneck for small and medium enterprises wanting to deploy AI solutions on the Edge, which, ultimately, slows down the adoption of AI on applications in our daily life. In this work, we present a modular AI pipeline as an integrating framework to bring data, algorithms, and deployment tools together. By removing the integration barriers and lowering the required expertise, we can interconnect the different stages of particular tools and provide a modular end-to-end development of AI products for embedded devices. Our AI pipeline consists of four modular main steps: (i) data ingestion, (ii) model training, (iii) deployment optimization, and (iv) the IoT hub integration. To show the effectiveness of our pipeline, we provide examples of different AI applications during each of the steps. Besides, we integrate our deployment framework, Low-Power Deep Neural Network (LPDNN), into the AI pipeline and present its lightweight architecture and deployment capabilities for embedded devices. Finally, we demonstrate the results of the AI pipeline by showing the deployment of several AI applications such as keyword spotting, image classification, and object detection on a set of well-known embedded platforms, where LPDNN consistently outperforms all other popular deployment frameworks.


Article Type:
scientifique
Faculty:
Ingénierie et Architecture
School:
HE-Arc Ingénierie
Institute:
Aucun institut
Date:
2020-08
Pagination:
25 p.
Published in:
ACM Transactions on Internet of Things
Numeration (vol. no.):
2020, vol. 1, no. 4, article no. 26
DOI:
ISSN:
2691-1914
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2020-08-25, last modified 2021-03-26

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)