I use “model” to refer to the machine learning model and “system” to refer to the infrastructure around it, including data pipeline and monitoring systems.
Table of contents
…. Level 1: Online predictions – your system can make predictions in real-time
……… Use cases
………… Problems with batch predictions
……… Solutions
………… Fast inference
………… Real-time pipeline
……………. Stream processing vs. batch processing
……………. Event-driven vs. request-driven
……… Challenges
…. Level 2: Online learning – your system can incorporate new data and update in real-time
……… Defining “online learning”
……… Use case
……… Solutions
……… Challenges
………… Theoretical
………… Practical
…. The MLOps race between the US and China
…. Conclusion
#machine learning #online learning #online predictions