W02 Workshop on System-level Design Methods for Deep Learning on Heterogeneous Architectures (SLOHA 2021)

Start
Friday, 5 February 2021 15:00
End
Friday, 5 February 2021 19:00
Important Dates
Submission Deadline for extended abstracts
Notification of acceptance (ext. abstracts)
Organizer
Frank Hannig, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Germany
Organizer
Paolo Meloni, University of Cagliari, Italy
Organizer
Matteo Spallanzani, ETH Zürich, Switzerland
Organizer
Matthias Ziegler, Fraunhofer Institute for Integrated Circuits (IIS), Erlangen, Germany
Keynote Speaker
Luca Benini, ETHZ, Switzerland
Keynote Speaker
Michaela Blott, Xilinx Research, Ireland
Speaker
Walther Carballo Hernández, Universit´e Clermont Auvergne, France
Speaker
Olivia Weng, University of California, San Diego, United States
Speaker
Mikail Yayla, TU Dortmund, Germany
Speaker
Dainius Jenkus, Newcastle University, United Kingdom
Speaker
Muhammad Sabih, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Germany
Speaker
Francesco Paissan, Fondazione Bruno Kessler, Italy
Speaker
Quentin Ducasse, ENSTA Bretagne, France
Speaker
Christopher Metz, University Bremen, Germany
Speaker
Cristina Chesta, Santer Reply SpA, Italy
Speaker
Etienne Dupuis, Lyon Institute of Nanotechnology, France
Speaker
Simon Pfenning, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Germany
Speaker
Sorin Grigorescu, Transilvania University of Brasov and Elektrobit Automotive, Romania
Speaker
Augusto Vega, IBM T. J. Watson Research Center, United States
SLOHA 2021: DATE Friday Workshop on System-level Design Methods for Deep Learning on Heterogeneous Architectures

 

Machine learning, particularly deep learning (DL), is the most quickly growing domain of artificial intelligence. DL is being applied in more and more disciplines for recognition, identification, classification, and prediction tasks. A large part of the activities is focused on image, video and speech processing, but more general signal processing tasks also benefit from DL.

Prominent application areas and markets include human-machine interaction using vocal commands, biological signals processing on wearable devices for medical and fitness applications, visual environment understanding applications such as those used in robotics and advanced driver assistance systems, or predictive maintenance in industrial automation. These applications are often embedded into a broader technical context, imposing stringent constraints on power and size. Thus, many applications should be executed on highly customized heterogeneous low-power computing platforms at the edge.

While on the one hand, there exists a large zoo of DL models and tools that target standard hardware platforms, there are many challenges when targeting heterogeneous and edge devices on the other hand. Several software and hardware design choices have to be made when developing such systems. How to automate the search for and efficiently deploy or synthesize a neural network on multiple target platforms, such as different heterogeneous low-power computing platforms and edge devices? How should the neural network look like to achieve the best possible result on a given hardware platform with limited computing power and energy budget?

The workshop's primary goal is to address these research questions and facilitate the implementation of DL applications on heterogeneous low-power computing platforms and edge devices, including accelerators such as (embedded) GPUs, FPGAs, CGRAs, and TPUs.

For further information and the workshop program, please visit:

https://www12.cs.fau.de/ws/sloha2021/

 

W02.O Welcome and Introduction

Session Start
Fri, 15:00
Session End
Fri, 15:10
Friday Workshops Co-Chair
Frank Hannig, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Germany
Friday Workshops Co-Chair
Paolo Meloni, University of Cagliari, Italy
Friday Workshops Co-Chair
Matteo Spallanzani, ETH Zürich, Switzerland
Friday Workshops Co-Chair
Matthias Ziegler, Fraunhofer Institute for Integrated Circuits (IIS), Erlangen, Germany

W02.K.1 Keynote Speech 1

Session Start
Fri, 15:10
Session End
Fri, 15:50
Keynote Speaker
Luca Benini, ETHZ, Switzerland
Presentations

W02.K1.1 In-Sensor ML — Heterogeneous Computing in a mW

Start
15:10
End
15:50
Keynote Speaker
Luca Benini, ETHZ, Switzerland

W02.K.2 Keynote Speech 2

Session Start
Fri, 18:15
Session End
Fri, 18:55
Keynote Speaker
Michaela Blott, Xilinx Research, Ireland
Presentations

W02.K.2.1 Specialization in Hardware Architectures for Deep Learning

Start
18:15
End
18:55
Keynote Speaker
Michaela Blott, Xilinx Research, Ireland

W02.C Closing

Session Start
Fri, 19:00
Session End
Fri, 19:05
Friday Workshops Co-Chair
Frank Hannig, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Germany
Friday Workshops Co-Chair
Paolo Meloni, University of Cagliari, Italy
Friday Workshops Co-Chair
Matteo Spallanzani, ETH Zürich, Switzerland
Friday Workshops Co-Chair
Matthias Ziegler, Fraunhofer Institute for Integrated Circuits (IIS), Erlangen, Germany