Site icon R-bloggers

Machine Learning in R with H2O and LIME: slides, photos and video

[This article was first published on MilanoR, and kindly contributed to R-bloggers]. (You can report issue about the content on this page here)
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

Hello, everyone! Did you have fun at June 25th’s workshop with H2O and Lime? If you were there, we’re sure you did. If you weren’t… here’s a recap, with the explanation, the link to the live event and all the materials too!

The workshop started at 19 in Mikamai, and it began with a bang! Joe Chow, evangelist of H2O, launched us right away into the world of Machine Learning. He presented to us AutoML, a framework for model’s training and comparison, which is able to fit and compare different model families with the use of few parameters. AutoML can be used for automating the machine learning workflow, which includes automatic training and tuning of many models within a user-specified time-limit. After introducing AutoML, Joe showed us LIME, a package for model interpretation.

If you want to know more, click on the link below to look at the slides or check the Github repo.


Automatic and Interpretable Machine Learning in R with H2O and LIME

by Jo-fai (Joe) Chow (Github repo)

 

Then, after the theory, we got practical. We met Moneyball, an app to detect the most promising baseball players that got payed less – the ones that’s worth investing on, basically. You can find both the slides and the demo below. The developers used different models as examples, both dataset free and proprietary, and then they built a shiny app to make it more easy for business experts – the ones who were going to buy the players.

 

Moneyball Demo (Public Version)

(GitHub)

 

If you’re more a listening type than a reading type of person, the full recording is available on our Facebook channel:

 

Meeting full video

 

 

After this dump of knowledge, we had pizza all together – offered by H2O and our sponsor Quantide. We were also featured in Joe’s famous 360° selfies, that’s now up in this Twitter! What an honor!

 

Thanks to @maryclaryf, @akirocode, Simone Scardapane and Gabriele Nocco, I had a great time in #Milan and #Rome two weeks ago. Here are the slides:@h2oai + LIME workshop:https://t.co/rLhgms8EEN

Moneyball:https://t.co/IpErAx77oE#AroundTheWorldWithH2Oai #360Selfie pic.twitter.com/Sydswaxsdb

— Jo-fai (Joe) Chow (@matlabulous) 11 luglio 2018

With full stomaches and full minds, the only thing we could do was have a chat together. We can’t thank Joe, H2O and Quantide enough for offering us this huge opportunity.

If you don’t want to miss out on these special occasions, follow our blog and subscribe to our newsletter. Thank you for reading till here and supporting us. Till next time!

The post Machine Learning in R with H2O and LIME: slides, photos and video appeared first on MilanoR.

To leave a comment for the author, please follow the link and comment on their blog: MilanoR.

R-bloggers.com offers daily e-mail updates about R news and tutorials about learning R and many other topics. Click here if you're looking to post or find an R/data-science job.
Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.