Call for Papers

AI and Machine Learning ( Kompaktseminar )

Practical Implementations for Deploying AI in Embedded

Referent: Markus Levy, NXP Semiconductors
Vortragsreihe: KS 2.4
Zeit: 07.12.18 09:00 - 15:30
Co-Referenten: Additional author names to be supplied.

Zielgruppe

Entwicklung

Themenbereiche

Analyse & Design, Implementierung

Schwerpunkt

Technologie

Voraussetzungen

Grundlagenwissen

Kurzfassung

This seminar will deliver a combination of theory, practical advice, and live demonstrations to explain how to implement machine learning for embedded applications. The seminar will conclude with an open Q&A with several machine learning experts

Gliederung

1. Concepts to enable embedded machine learning
2. Successful machine learning implementations including chip companies, software tools, applications.
3. AI/ML primer
* Comparing frameworks and models for Neural networks and classical machine learning
* Standards and libraries
4. Vision, voice, sensors
5. Acceleration solutions
* Taking advantage of hardware features
* Running neural networks on existing platforms:
* CPUs (e.g. Cortex A53, M7, x86)
* GPUs:(e.g. Nvidia, Arm, Verisilicon, Qualcomm)
* DSPs: Hexagon 546, 685
6. OpenCV for TensorFlow and Caffe models
7. Machine learning algorithms
8. Neural networks -optimize and deploy trained NN models
9. Cloud Deployment including model training and optimization for edge nodes
10. Machine learning front ends
* Vision
* Voice
* Sensors
11. Workflows -Gathering training data, deployment, model evaluation and improvement
12. Demonstrations
* Face recognition platform
* Anomaly detection system
* Person detection on edge platforms
13. Q&A with several machine learning experts

Nutzen und Besonderheiten

Participants will learn from several machine learning experts, coming together to provide a well-rounded curriculum that will allow engineers and programmers to have a clear understanding of machine learning.

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.