Back to results
US 2025/0053885 A1Published application
Method and System Based on Using a Model Collection for Explanation of Machine Learning Results
AssigneeABB Schweiz AG
InventorsBenedikt Schmidt, Benjamin Kloepper, Arzam Muzaffar Kotriwala, Yemao Man, Dawid Ziobro, Gayathri Gopalakrishnan, Joakim Astrom, Marcel Dix, Divyasheel Sharma
Life of this patent
Estimating the term…
Abstract
A method for explanation of machine learning results based on using a model collection includes training at least two machine learning models with at least two competing strategies for the at least one dataset; and using the least two machine learning models to yield at least two different predictions and/or at least two explanations for the at least one dataset.
Claims13
A method for explanation of machine learning results based on using a model collection, the method comprising:
- training at least two machine learning models with at least two competing strategies for at least one dataset;
- and
- using the least two machine learning models to yield at least two different predictions and/or at least two explanations for the at least one dataset.
Dependencies are inferred from the claim text.