Littering and...MLOps!
|
|
|
|
IMPORTANT TIMING UPDATE!!! We are back to normal schedule for the meetups which means 9am West coast US time and 5pm UK. See you there.
|
|
|
|
|
|
|
|
|
|
|
“The man who does not read has no advantage over the man who cannot read.” - Mark Twain
This Friday we are back at it with another session of the reading club. Which paper will we be reading?
"150 Successful Machine Learning Models: 6 Lessons Learned at Booking.com" If we are really lucky and enough people tweet at the authors maybe we can get them to join on their Friday night!? Actually i just did a twitter search for them and couldn't find their handles so if anyone knows it share em with the rest of us!
Because the event is being run by the ulta organized Charlie You he created a place for you to submit and vote on discussion topics here.
|
|
|
|
|
|
|
|
|
|
|
|
|
Category Creation
So much that I wasn't able to ask Josh Tobin on last week's meetup none the less he still produced some serious aha moments for me when it came to looking at the ML development cycle and how there is a hole to be filled by the eval store! Quick tips from Josh on testing, "its not enough to run the ML model once on a
big data set and get a score out of it" What should we do then? Check out the video here and podcast here for the full story.
|
|
|
|
|
|
|
|
|
|
|
|
|
Lessons Learned From Meetup #1
As you have heard its been 1 year since we officially started holding the weekly meetups. So as a tip of the hat to my old boss Luke Marsden I wrote about the key takeaways around collaborating as a data scientist and why its not as easy as traditional software development.
Huge shout out to Luke who was the only one crazy enough to think a community
around was worthwhile. If you wanna see the first meetup I drew my inspiration for the blog from click here.
|
|
|
|
|
|
|
|
|
|
|
|
|
Get There, And Stay There!
Ben wrote a book that had the same name as another book. He changed the title of the book. We are now left with "Machine Learning Engineering in Action"
Meetup: Model Watching: Keeping Your Project in Production. Some key takeaways you can expect are:
- Understanding why attribution and performance monitoring is critical for long-term project success
- Borrowing hypothesis testing,
stratification for latent confounding variable minimization, and statistical significance estimation from other fields can help to explain the value of your project to a business
- Unlike in street racing, drifting is not cool in ML, but it will happen. Being prepared to know when to intervene will help to keep your project running.
Bio: Ben Wilson has worked as a professional data
scientist for more than ten years. He currently works as a resident solutions architect at Databricks, where he focuses on machine learning production architecture with companies ranging from 5-person startups to global Fortune 100. Ben is the creator and lead developer of the Databricks Labs AutoML project, a Scala-and Python-based toolkit that simplifies machine learning feature engineering, model tuning, and pipeline-enabled modeling. He's the author of Machine Learning Engineering in Action, a primer on building, maintaining, and extending production ML projects.
+ As always see you at 5pm GMT / 9am PST tomorrow, Wednesday by clicking the link below.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
