Loading…
Linaro Connect resources will be available here during and after Connect!

Booking Private Meetings
Private meetings are booked through bkk19.skedda.com and your personal calendar (i.e. Google Calendar). View detailed instructions here.

For Speakers
Please add your presentation to Sched.com by attaching a pdf file to your session (under Extras > + File). We will export these presentations daily and feature on the connect.linaro.org website here. Videos will be uploaded as we receive them (if the video of your session cannot be published please let us know immediately by emailing connect@linaro.org).

Puzzle: 
Dave Pigott has come up with another puzzle: https://linaro.co/bkk19puzzle can you crack the code?! Prizes will be awarded to the winner(s) on Friday.




Sign up or log in to bookmark your favorites and sync them to your phone or calendar.

Machine Learning/AI [clear filter]
Tuesday, April 2
 

2:00pm

BKK19-TR05 Arm NN and the plug-in framework

This tutorial will describe the internals of the Arm NN SDK and will focus on its plug-in framework. Attendees will learn how to write a plug-in to add support for the NN processing unit in the SoC by their companies.

Speakers
NP

Narumol Prangnawarat

Senior Engineer, Arm
avatar for Matteo Martincigh

Matteo Martincigh

Staff Engineer, Arm
LB

Les Bell

Staff Engineer, Arm



Tuesday April 2, 2019 2:00pm - 2:55pm
Session Room 3 (Lotus 10)
 
Wednesday, April 3
 

2:00pm

BKK19-321 FPGAs for Highest Performance Inference
GPUs are often used to accelerate machine learning inference as they offer improvements in performance over standard processors. FPGAs, however, have unique capabilities that offer performance advantages over both CPUs and GPUs. This session will introduce those capabilities and explore some metrics.

Speakers
avatar for Craig Abramson

Craig Abramson

Marketing, Xilinx
Experienced Technical Marketing Engineer with over 20 years experience in the semiconductor industry, most of them with Xilinx as both a Field Application Engineer and more recently, in marketing. Prior to that, did actual embedded design on the earliest 32-bit processors for both... Read More →



Wednesday April 3, 2019 2:00pm - 2:25pm
Session Room 3 (Lotus 10)
 
Thursday, April 4
 

8:30am

BKK19-402 Inferencing at the edge and Fragmentation Challenges
As deep learning (DL) expands is application into ever more areas, DL at the edge has become an area of rapid innovation and has also become highly fragmented. This creates a challenge in the ecosystem for framework providers that want to take advantage of specialized hardware, and an equal challenge for SoC providers, or makers of DL accelerators that need to support various frameworks, customer innovations, device constraints, etc. This talk will explore what constitutes DL at the edge, it will highlight the recent trends in this area from runtimes and compilers, to model formats, and explore the challenges, and scalability needs of collaborative solutions.

Speakers
avatar for Mark Charlebois

Mark Charlebois

Director Engineering, Qualcomm Technologies Inc, Qualcomm Technologies Inc
Presently in QCT for Qualcomm Technologies Inc (QTI), working on a Deep Learning framework for Qualcomm SoCs and as an open source software strategist. Mark has represented QTI on the Linux Foundation board, and served on the Dronecode board, and Core Infrastructure Initiative steering... Read More →



Thursday April 4, 2019 8:30am - 9:25am
Keynote Room (World Ballroom BC)
 


Twitter Feed