Continual Learning in Practice

03/12/2019
by   Tom Diethe, et al.
0

This paper describes a reference architecture for self-maintaining systems that can learn continually, as data arrives. In environments where data evolves, we need architectures that manage Machine Learning (ML) models in production, adapt to shifting data distributions, cope with outliers, retrain when necessary, and adapt to new tasks. This represents continual AutoML or Automatically Adaptive Machine Learning. We describe the challenges and proposes a reference architecture.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset