Learn how to use the Intel® Movidius™ Neural Compute Stick and open source frameworks to deploy deep neural networks at the edge.

Workshop details

Market research estimates there will be as many as 20 billion connected devices in the market by 2020. These devices are expected to generate billions of petabytes of data traffic between cloud and edge devices. In 2017 alone, 8.4B connected devices are expected in the market which is sparking a strong need to pre-process data at the edge. This has led many IoT device manufacturers, especially those working on vision based devices like smart cameras, drones, robots, AR/VR, etc., to bring intelligence to the edge.

Through the recent addition of the Movidius™ VPU technology to its existing AI edge solutions portfolio, Intel is well positioned to provide solutions that help developers and data scientists pioneer the low-power intelligent edge devices segment. This workshop will provide hands-on experience with Intel’s Neural Compute Stick – a low-cost, form-factor developer kit for low-power vision based embedded inference applications.

What You Will Learn:

• Insights into how Movidius™ VPUs are pioneering DNN accelerated vision processing.
• Introduction to hardware and software components of NCS.
• Workflow of network profiling and application development using NCS.
• Detection/Classification models
• Advanced functionalities
• Hands-on with advanced demos and sample codes built using NC SDK’s API framework, which includes support for Caffe and TensorFlow

Participant requirements

** Participants are required to bring a laptop computer with Ubuntu 16.04 and Neural Compute SDK installed **

What is provided

• NCS hardware will be provided for use during the workshop
• A light lunch will be provided and please ensure that any dietary requirements are made clear during registration

Hosted by

The workshop will be hosted by Intel engineers.

This workshop is free to attend and hosted by Intel in partnership with the BCS Open Source Specialist Group and the Open Source Hardware User Group.

Note: Please aim to arrive by 08:45 as the workshop will start at 09:00 prompt.

We start the new year with an event on the theme of open source musical software and hardware.

Bela, an embedded platform for ultra-low latency audio and sensor processing

Bela started off as a research project at Centre For Digital Music (Queen Mary University of London) and is now a commercial product, mainly aimed at makers, programmers and researchers that work with audio. The platform is based on a BeagleBone Black with a custom expansion cape and a dedicated software environment. The board runs Debian Linux with Xenomai as a real-time co-kernel. The combined use of Xenomai and the BeagleBone Black’s on-board PRU microcontroller allows to achieve sub-millisecond latency for audio and sensor processing, while node.js is used to provide a user-friendly web-based IDE. The project is entirely open source, hardware and software.

Giulio Moro is a PhD student in the Centre for Digital Music at Queen Mary University of London. A sound engineer by training, he is now researching in the field of performer-instrument interaction. He is one of the inventors and core developers of Bela.

Female Laptop Orchestra: exploring geographical, cultural, technical and artistic challenges of collaborative music making

As a collective of female musicians, artists, engineers, computer scientists and researchers, Female Laptop Orchestra has been pushing the boundaries of technology and cross-cultural co-located and distributed collaborative music making since 2014. Besides musical instruments, we use a variety of open source and commercial tools to create music, stream music and connect with our audience during the performance. We often collaborate with classical composers and ensembles, filmmakers, visual designers, choreographers and dancers. Recently, we also collaborated with members of Women in Music Technology (a student organization whose goal is to encouraging more women to join the music tech field of study and highlight the often unsung role of women in music technology, based at Georgia Tech Centre for Music Technology in US) and Sonora (a collaborative network bringing together artists and researchers interested in feminist manifestations in the context of the arts, based in Brazil).

Nela Brown is a sound artist, technologist, researcher and educator. In the past decade, she composed music and designed sound for award-winning projects including theatre performances, dance, mobile, film, documentaries and interactive installations. She is the founder of the Female Laptop Orchestra (FLO), an eclectic group of female musicians and technologists exploring co-located and distributed collaborative music making within different contexts and across different geographical locations. As a creative director of FLO since 2014, Nela co-ordinated 7 national and international FLO performances involving 36 collaborators from 21 different countries.

Talk #3 TBA

Note: Please aim to arrive by 18:15 as the event will start at 18:30 prompt.

Closing date for bookings is Tuesday 16th January 2018 at 11:30 pm. No more bookings will be taken after this date. For overseas delegates who wish to attend the event please note that BCS does not issue invitation letters