Introduction

On line machine learning is a different paradis of performing predictions. What are the consequences of this to the infera structure that you are going to consider to serve this online rning in production? And especially in the last couple of years, there have been more and more people speaking about even driven architectures or streaming architecture. So apparently they have seen the light, and we have been doing all things wrong so far. That at least that's what these people claim, or are claiming.