Keynote speaker
David Atienza, EPFL - Edge Computing Design in the Big Data Era- The Internet of Things (IoT) has been hailed as the next frontier of innovation in which our everyday objects are connected in ways that improve our lives and transform industries. The IoT concept is poised to reach 70 billion connected devices by 2025, but major key challenges remain in achieving this potential due to inherent resource-constrained nature of IoT systems, coupled with the computing power requirements of Big Data applications, which can result in degraded and unreliable behavior of IoT nodes, or a global energy crisis when IoT is fully deployed in the future. In this keynote, I will first discuss the challenges of ultra-low power design and communication in IoT nodes. Then, he will showcase the opportunities in wearables and next-generation consumer electronics for next-generation smart IoT nodes to deliver edge computing. This new edge computing architectures combine new multi-core embedded systems with neural network accelerators, as well as including novel nanotechnologies, to gracefully scale the energy consumption and precision of the IoT application outputs according to the requirements of our surrounding world, as living organisms do to operate efficiently.
Workshop Schedule
The workshop is organized in two sessions: 1) “Architectures and design methodologies to support embedded intelligence”, 2) “Embedded Intelligence: best practices and software support” and for an exciting full-immersion day.Workshop introduction
- 09:00-09:15 Welcome and presentation of the workshop program
- 09:15-10:00 Keynote: David Atienza, EPFL - Edge Computing Design in the Big Data Era
- 10:00-10:30 Networking & Coffee break
- 10:30-10:50 Exploring IoT Platform with Technologically Agnostic Processing-in-Memory Framework, Paulo Cesar Santos, João Paulo Cardoso de Lima, Rafael F. Moura, Hameeza Ahmed, Marco Antonio Zanata Alves, Antonio C. S. Beck and Luigi Carro
- 10:50-11:10 A Low-cost Energy Consumption Measurement Platform, Nadir Cherifi, Alexandre Boe, Thomas Vantroys, Colombe Hérault and Gilles Grimaud
- 11:10-11:30 HW/SW Co-Design and Co-Optimizations for Deep Learning, Alberto Marchisio, Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif and Muhammad Shafique
- 11:30-12:30 Poster session
- An unsupervised approach for automotive driver identification, Nicholas Mainardi, Michele Zanella, Federico Reghenzani, Niccolò Raspa and Carlo Brandolese
- Blockchain-based Edge Computing for Deep Neural Network Applications, Jae-Yun Kim and Soo-Mook Moon
- 12:30-14:00 Lunch
- 14:00-14:20 Invited paper ALOHA: an architectural-aware framework for deep learning at the edge, Paolo Meloni, Daniela Loi, Gianfranco Deriu, Andy D. Pimentel, Dolly Sapra, Bernhard Moser, Natalia Shepeleva, Francesco Conti, Luca Benini, Francesca Palumbo, Michael Masin, Oscar Ripolles, David Solans, Maura Pintor, Battista Biggio, Todor Stefanov, Svetlana Minakova, Nikos Fragoulis and Ilias Theodorakopoulos
- 14:20-14:40 Fog Vs. Cloud Computing: Should I Stay or Should I Go?, Flávia Pisani and Edson Borin
- 14:40-15:00 Back to the Future: Resource Management in Post-Cloud Solutions, Michele Zanella, Giuseppe Massari and William Fornaciari
- 15:00-16:00 Networking & Coffee break
- 16:00-16:20 Towards plug&play Smart Thermostats inspired by Reinforcement Learning, Charalampos Marantos, Christos Lamprakos, Vasileios Tsoutsouras, Kostas Siozios and Dimitrios Soudris
- 16:20-16:40 A Compression-Driven Training Framework for Embedded Deep Neural Networks, Matteo Grimaldi, Federico Pugliese, Valerio Tenace and Andrea Calimera
- 16:40-17:00 Closing remarks