Machine Learning

AI och maskininlärning i inbyggda system

(gratis seminarium)


Kista: 7 maj kl. 13:00-16:30
- FULLBOKAT. Anmäl dig till "väntelistan"

Göteborg: 8 maj kl. 08:30-12:00
- Några platser kvar

Kontakt information

Mikael Johnsson
+46 (0) 40 59 22 01
mikael.johnsson@nohau.se

AI-tekniken har utvecklats och är redan mogen för många tillämpningar i inbyggda system. Särskilt vid utveckling av autonomi i mobila maskiner är maskininlärning i realtid nyckeln. En autonom maskin fungerar i en miljö där saker som inte alltid är logiska eller rationella händer. Hur kan maskinen få medel att klara sig och arbeta effektivt?

Seminariet tar upp några av utmaningarna med AI och ML samt visar på lösningar i form av färdiga programpaket för bl.a. Neurala Nätverk. Vi visar också en praktisk tillämpning för objektigenkänning och berättar hur du skapar en sådan.

Agenda:

AI and intelligence in the embedded world. Martin Rugfelt, Sentian.AI
Project Trillium, Unleashing Innovation for ML on Arm. Gilles Augustins, ARM
Getting up to speed on visual recognition with deep learning on embedded devices. Kalevi Ratschunas, Nohau Solutions


AI and intelligence in the embedded world

The speed of development is relentless and new solutions show up all the time. New technology will have a tremendous impact on all businesses. We will look at examples from autonomous heavy equipment to small low powered solutions. We will also look at some of the aspects around AI and machine learning and what needs to be considered when developing these kind of solutions in the context of different examples.

Speaker: Martin Rugfelt is CEO and founder of Sentian.ai, an AI company focused on transformative industrial AI solutions. Entrepreneur with more than 10 years of applied Artificial Intelligence experience. Prior to AI he worked with mobile applications, telecoms and internet solutions for both large and small companies. He is also currently advising a few startups in the space of NLP, Computer vision and search. Martin serves on the board of Lytics.ai a predictive healthcare company.

Project Trillium, Unleashing Innovation for ML on Arm

Project Trillium, Arm’s Machine Learning (ML) platform, enables a new era of advanced, ultra-efficient inference at the edge. Specifically designed for ML and neural network (NN) capabilities, the architecture is versatile enough to scale to any device, from IoT to connected cars and servers. Built from the ground up for optimal performance and efficiency, Project Trillium completes the Arm Heterogenous ML compute platform with the Arm ML processor, the second-generation Arm Object Detection (OD) processor and open-source Arm NN Software Design Kit.

Speaker: Gilles Augustins is driving Arm Software and Development Tools sales in Europe, and is involved in shaping Arm Machine Learning tools strategy. He’s been with Arm for ten years, in many sales and business development positions, covering partners across Europe for CPUs, silicon libraries and software products.

Getting up to speed on visual recognition with deep learning on embedded devices

In this talk I will walk through what it takes to get an embedded system up and running machine learning and the performance that can be expected.
We will show 3 different configurations of different performance levels running. A quick overview of Transfer learning, comparison of existing recognition models and also model conversion for specific hardware accelerators.

Speaker: Kalevi Ratschunas’ career spans 20 years in the fields of smart phones, embedded and IoT. He has been part of great consumer products coming to life in the mobile and semiconductor industries. In his current role he works on machine learning projects and supports embedded SW development tools.

Välkommen!

Sista anmälningsdag till detta gratisseminarium: 18 april (först till kvarn…)

Kista: 7 maj kl. 13:00-16:30
Adress: Kista Science Tower, Färögatan 33, Kista

Göteborg: 8 maj kl. 08:30-12:00
Adress: Radisson Blu Scandinavia Hotel, Södra Hamngatan 59, Göteborg (Obs! ny adress)

Önskar du mer information?

Behöver du en offert, information eller råd. Kontakta oss!