Kicking off another year of reactive machine learning

Here’s a quick update on what’s been going on with reactive machine learning and what’s up next.

I gave a talk on reactive data collection at Scala eXchange. Check out the video for a rapid-fire intro to using distributed fact databases in a machine learning system.

Next up, I’ll be speaking at Spark Summit East on reactive feature generation. With all of the exciting progress in the Spark ecosystem, I expect that the conference will yield lots of worthwhile discussion around the union of reactive and machine learning.

The book for Manning is progressing nicely and should be launched into Early Access very soon. I’ve found it very helpful to develop the ideas for the book and then test them out in conference talks to get feedback. I’m looking forward to being able to share these longer, more detailed versions of the ideas very soon. Look out for another update post from me when it finally goes live.

Of course, I’ve still been blogging about all of this stuff, as you might expect. If I could recommend one recent post of interest, I’d point you to this one on whether to organize pipelines using orchestration or composition.

If you have any ideas about new libraries or approaches that might be relevant to reactive machine learning, don’t hesitate to reach out. I’d love to hear from you here on Medium or on Twitter.