US Patent Application 18027061. METHODS AND SYSTEMS FOR UPDATING MACHINE LEARNING MODELS simplified abstract

From WikiPatents
Jump to navigation Jump to search

METHODS AND SYSTEMS FOR UPDATING MACHINE LEARNING MODELS

Organization Name

Telefonaktiebolaget LM Ericsson (publ)


Inventor(s)

Johan Haraldson of Stockholm (SE)


Ezeddin Al Hakim of London (GB)


Henrik Eriksson of Enskede (SE)


Yeongwoo Kim of Kista (SE)


METHODS AND SYSTEMS FOR UPDATING MACHINE LEARNING MODELS - A simplified explanation of the abstract

  • This abstract for appeared for US patent application number 18027061 Titled 'METHODS AND SYSTEMS FOR UPDATING MACHINE LEARNING MODELS'

Simplified Explanation

The abstract describes a method and system for updating machine learning (ML) models. The method is performed by a client computing device. Initially, a first ML model is obtained, which is designed to take input data and generate an output data set. Then, a second ML model is trained using the input data set and the first output data set. The result of this training is a third ML model. Finally, the third ML model is deployed, indicating that it is ready for use.


Original Abstract Submitted

Methods () and systems () for updating ML models. The method is performed by a client computing device (()). In one aspect, the method comprises obtaining (s) a first machine learning (ML) model. The first ML model is configured to receive input data set and to generate first output data set. The method further comprises training (s) a second ML model based at least on the input data set and the first output data set, obtaining (s), as a result of training the second ML model, a third ML model, and deploying the third ML model.