Method And System For Knowledge Transfer Between Different Ml Model Architectures

Abstract: This disclosure relates to a method and system for managing knowledge of a primary ML model (102A). The method includes generating a set of class probabilities for an unlabelled dataset based on a labelling function. The unlabelled dataset may be associated with the primary ML model (102A), and the primary ML model(102A) may employ a first ML model architecture (102B). Further, the method includes transferring the unlabelled dataset and the associated set of class probabilities for training a secondary ML model (103A) based on a knowledge transfer technique. The secondary ML model (103A) may employ a second ML model architecture (103B). It should be noted that the first ML model architecture (102B) may be different from the second ML model architecture (103B).

Patent Information

Applicants

Inventors

Specification

Documents

Application Documents