METHOD FOR ANALYZING CLASS SIMILARITIES IN A MACHINE LEARNING MODEL

A method is provided for analyzing a similarly between classes of a plurality of classes in a trained machine learning model (ML). The method includes collecting weights of connections from each node of a first predetermined layer of a neural network (NN) to each node of a second predetermined layer...

Full description

Saved in:
Bibliographic Details
Main Authors Derks, Gerardus Antonius Franciscus, van Vredendaal, Christine, Michiels, Wilhelmus Petrus Adrianus Johannus, Ermans, Brian
Format Patent
LanguageEnglish
Published 03.03.2022
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:A method is provided for analyzing a similarly between classes of a plurality of classes in a trained machine learning model (ML). The method includes collecting weights of connections from each node of a first predetermined layer of a neural network (NN) to each node of a second predetermined layer of the NN to which the nodes of the first predetermined layer are connected. The collected weights are used to calculate distances from each node of the first predetermined layer to nodes of the second predetermined layer to which the first predetermined layer nodes are connected. The distances are compared to determine which classes the NN determines are similar. Two or more of the similar classes may then be analyzed using any of a variety of techniques to determine why the two or more classes of the NN were determined to be similar.
Bibliography:Application Number: US202017002978