Abstract
News editors obtained the following quote from the background information supplied by the inventors:“In several network automation use cases, the required ML models should not cover the complete networkin one ML model instance. A model instance needs to be trained to learn the specific characteristics of eachlocal context, for example in use cases that depend on the local radio propagation environment, such asmobility prediction and positioning. To include all local contexts into one single ML model instance wouldmake it impractically large for several reasons. Simply, the size of the required ML model instance maybecome a problem and a single monolithic instance doesn’t allow for different ML lifecycles (deployment,training, retraining etc.) for each of the local contexts.
NETL
NSTL