SYSTEM AND METHOD FOR SPATIAL SALIENCY EXPLANATION FOR TIME SERIES MODELS

Example aspects include techniques for spatial saliency explanation for Time Series machine learning models. These techniques may include identifying, based on a token-based importance method, a plurality of tokens of a predefined importance to a machine learning (ML) inference. In addition, the tec...

Full description

Saved in:
Bibliographic Details
Main Authors LOHIA, Pranay Kumar, PANWAR, Naveen, PATRO, Badri Narayana
Format Patent
LanguageEnglish
Published 08.08.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Example aspects include techniques for spatial saliency explanation for Time Series machine learning models. These techniques may include identifying, based on a token-based importance method, a plurality of tokens of a predefined importance to a machine learning (ML) inference. In addition, the techniques may generating frequency distribution information based on the plurality of tokens of the predefined importance, and generating, based on the frequency distribution information, quantile information for the plurality of tokens of a predefined importance. Further, the techniques may include calculating spatial saliency information based on the frequency distribution information and quantile information, the spatial saliency information including a spatial saliency value for a quantile of the quantile information, and presenting the spatial saliency information via a graphical user interface.
Bibliography:Application Number: US202318163711