Welcome to the 31st PyData Cambridge virtual meetup!

This is a virtual meetup. We will use zoom, login details published closer to the date.

Thanks a lot to our sponsors: NumFOCUS, ARM, Fetch.ai and the Raspberry Pi foundation.

Agenda

19:00 - Introduction
19:15 - "Features Stores: What's all the hype about?" - Bojan Miletic
19:45 - Interval
19:50 - "The Future of ML is Tiny" - Pete Warden
20:20 - End
Note: this meetup will be recorded.

Code of Conduct

PyData is dedicated to providing a harassment-free event experience for everyone, regardless of gender, sexual orientation, gender identity, and expression, disability, physical appearance, body size, race, or religion. We do not tolerate harassment of participants in any form.

The PyData Code of Conduct governs this meetup. ( http://pydata.org/code-of-conduct.html ) To discuss any issues or concerns relating to the code of conduct or the behavior of anyone at a PyData meetup, please contact NumFOCUS Executive Director Leah Silen (leah@numfocus.org) or organizers.

Talk 1

"Features Stores: What's all the hype about?" by Bojan Miletic

Abstract:

• We'll cover some of functionalities for feature stores,
• How they can help you with your ML workflows
• When not to use them :)
• Brief overview of solutions on market

Bojan has been working with Python and ML related stuff for almost a decade. During his career experience, he had the opportunity to work with companies of all sizes: from several employees to several hundreds employees. He helped them on creating PoC, as well as getting existing solutions into production.

Talk 2

"The Future of ML is Tiny" by Pete Warden

Abstract:
In this talk, Pete will cover how to run machine learning models on tiny, cheap, battery-powered devices, and why this new approach opens up so many exciting applications. He'll show you how you can emulate a complete Arduino board from a Python Colab notebook, enabling you to get started for free, without any hardware. He'll also demonstrate using BLE technology to transfer models without cables, and cover using Colab to train and deploy quantized models.

Pete Warden is the technical lead of the TensorFlow Lite Micro open source machine learning framework at Google, and was previously CTO of Jetpac, acquired in 2014. He's the author of the TinyML O'Reilly book, blogs at petewarden.com, and is on Twitter as @petewarden.