Скачать или смотреть AI Tech Talk: Build custom keyword detection models for Arm Virtual Hardware with Qeexo AutoML

Register today for upcoming Arm Tech Talks: https://www.arm.com/techtalks

Get ready for another one of our Arm Tech Talks! Every fortnight, we discuss and explore some of the latest trends, technologies and best practices in the world of AI, featuring partners from the AI Ecosystem as well as speakers across Arm.

00:00 Start of Talk
02:12 Summary of Arm Announcements
03:55 Meet the presenters
04:43 Qeexo AutoML Overview
10:44 Qeexo AutoML & AVH
25:20 Demo of Qeexo AutoML on AVH
33:30 Q&A

The ability to detect keywords or specific sounds from microphone data to wake up the rest of an edge IoT system is a key enabler to minimize power usage for many applications. The Arm Virtual Hardware platform allows system developers to simulate the performance of an entire IoT system before the hardware is available. Enabling early development of firmware and specifications for complex system behavior like power-modes being triggered by machine learning models is a key application of the Arm Virtual Hardware platform.

Qeexo AutoML is an end-to-end framework for developing machine learning solutions for sensor-enabled embedded devices, covering all steps from data collection to deployment. The Qeexo AutoML platform has recently been enabled to integrate seamlessly with the Arm Virtual Hardware platform for the Arm Cortex-M55 processor and enhanced to better support keyword detection problems.

This talk will demonstrate training a custom keyword detection model and emulating its execution on the Arm Virtual Hardware Platform. We will also discuss some of the keyword-detection specific machine learning techniques applied automatically within the no-code Qeexo AutoML platform.

If you enjoyed this video, please subscribe to our channel and make sure to add us on Twitter so you can get a lot more content like this delivered straight to your feed!
  / armsoftwaredev