Call for Papers

Deploying AI and Machine Learning for the IoT ( Vortrag )

Edge Computing Applied to Auto and Industrial Applications

Referent: Markus Levy, NXP Semiconductors
Vortragsreihe: Machine Learning
Zeit: 06.12.18 09:45-10:25
Co-Referenten: TBD

Zielgruppe

Entwicklung

Themenbereiche

Analyse & Design, anderes Themengebiet

Schwerpunkt

Technologie

Voraussetzungen

Grundlagenwissen

Kurzfassung

While AI, neural networks, and classical machine learning algorithms have been around for decades, these technologies have improved 1000x in 3 years - this presentation will begin by explaining the technical and business reasons that led to this improvement. The availability of this technology is being capitalized on by the rapid expansion of the IoT, where many industries realized that it was impractical and potentially insecure to push all data up to the cloud - Markus Levy will present various methods for edge computing, with a focus on the 3Vs for automotive and industrial applications: Vision, Voice, and Vibration (covering sensors and anomaly detection). The presentation will also discuss cascading for interacting with gateways and the cloud, allowing machine learning to span from low-end MCUs to high-performance SoCs and accelerators to the infinitely-resourced cloud.

Gliederung

* Introduction to AI and machine learning
-Quick history
-Modern technologies for neural networks and machine learning
-Key applications that benefit from this technology
-General terminology
* Deciding when and where to apply edge computing versus the cloud
* What type of edge computing - classical or neural nets
-Including pros and cons
* Discussion about Vision, Voice, and Vibration
-Each has a place in automotive and industrial applications
-Supporting software structure (e.g. inference engines)
-Supporting hardware structure (e.g. cameras, sensors)
* Cascading (otherwise known as hybrid approach)
-Moving up the performance and resource ladder
-Deciding factors: inference time, memory capacity, etc.
* Benchmarking techniques
* Summary

Nutzen und Besonderheiten

Even in this day, many people don't even know how to spell machine learning (ok, this is an exaggeration) so this presentation on primary principles will help the development engineer and manager make decisions and gain ideas for how and why to implement AI, machine learning, and edge compute (there's a reason why i call these three terms out separately, as will be described in the presentation). Although the attendee cannot become an AI expert after this presentation, as this takes years, they will gain the insight into some of the key aspects of using this technology.

Über den Referenten

Markus Levy joined NXP in 2017 as the Director of Enabling Technologies. In this position, he is primarily focused on the strategy and development of AI and Machine Learning capabilities for NXP's microcontroller and i.MX product lines. Markus is also Chairman of the Board of EEMBC, which he founded and ran as the President since April 1997. Mr. Levy is also President of the Multicore Association, which he co-founded in 2005.