Things I Wish I Knew Before Building Serverless ML Solutions (Cloud Next '19)

Опубликовано 11 апреля 2019, 18:48

Building ML models for a proof-of-concept app is easy. To deploy them in a production system is hard. It becomes even more challenging when you have to keep your models fresh by retraining them every day.

These challenges are faced by every team working on deploying their ML solutions. The session will demonstrate how Omni Labs is doing this process in a serverless manner. After the talk you should be able to reason about your ML models and architect serverless ML pipelines.

Building Serverless ML Solutions → bit.ly/2TRpWhe
ML Engine → bit.ly/2TSxT5L

Watch more:
Next '19 Serverless Sessions here → bit.ly/Next19Serverless
Next ‘19 All Sessions playlist → bit.ly/Next19AllSessions

Subscribe to the GCP Channel → bit.ly/GCloudPlatform

Speaker(s): Martin Omander, Vikram Tiwari

Session ID: SVR301

event: Google Cloud Next 2019; re_ty: Publish; product: Cloud - Data Analytics - Dataflow, Cloud - Data Analytics - BigQuery; fullname: Martin Omander, Vikram Tiwari;