Jim Dowling

"Surf height predictions at Lahinch with a Serverless ML System in 100% Python"

Many machine learning models never make it to production. Apart from your model, you need at least three programs to build a production ML system:
* a feature pipeline to transform (new) input data into features;
* an inference pipeline turns features into predictions;
* a service/product/application/UI that is enhanced with add "intelligence" using the model and input data.
In this talk, we show you how to take the next step after training models. We show you how to build a serverless ML system. We will work with the important problem of predicting wave heights at Lahinch beach in County Clare. The system is written in only Python. It is hosted on free serverless services - Github (compute, UI) and Hopsworks (features, models).

Mini Bio : Jim Dowling is CEO of Logical Clocks and an Associate Professor at KTH Royal Institute of Technology. He is lead architect of the open-source Hopsworks platform, a horizontally scalable data platform for machine learning that includes the industry’s first Feature Store.

If you want to submit a talk proposal, please do so here: http://python.ie/meetups

If you wish to sponsor a venue, please contact meetups@python.ie