Event Details

Accessible ML: combining Open Source and Open Data

If you think that only big tech companies or PhD scientists can use ML & AI, I'd like to show you that an individual open-source enthusiast can build and train a model on comodity hardware using Open Data - and then scale that up on a public cloud.

If you're a gamer and a python developer, you might already have all the tools you need!

* fast.ai, an easy-to-learn Python ML framework
* nvidia-docker on an Ubuntu Gaming PC
* public-domain GIS imagery
* a couple terabytes of storage space and a fast internet connection

This talk grew out of the Firewise project, which I helped bootstrap last year. We aimed to use public-domain sattelite imagery to help predict and prevent forest fires. Even though the founders chose not to pursue this as a business, it's an excellent example of how easily open source and public data can be combined to benefit society.

What can I expect to learn?

- discussion of open source ethos, enabling independent development efforts, social causes.

- raising awareness of public-domain Open Data

- introduction to ML tools which are easy enough for any Python developer to adopt - no data science background needed!

Wednesday, May 1, 9:50am-10:30am
Will be recorded
Difficulty Level: Beginner
Aeva is an outspoken open source advocate with over a decade experience contributing to F/OSS software and communities. They have been building distributed systems on Linux-based systems since '99, and are most well known for their work in the OpenStack community wherein they founded Ironic, the Bare-Metal-as-a-Service project. Aeva lives in rainy Seattle and enjoys staying home when not... FULL PROFILE