The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
May. 09, 2023

Filed:

Oct. 12, 2019
Applicant:

International Business Machines Corporation, Armonk, NY (US);

Inventors:

Youssef Mroueh, New York, NY (US);

Tom Sercu, New York, NY (US);

Mattia Rigotti, New York, NY (US);

Inkit Padhi, White Plains, NY (US);

Cicero Nogueira Dos Santos, Montclair, NJ (US);

Attorneys:
Primary Examiner:
Int. Cl.
CPC ...
G06F 17/00 (2019.01); G06N 5/04 (2023.01); G16B 20/00 (2019.01); G16B 40/00 (2019.01); G06N 20/00 (2019.01);
U.S. Cl.
CPC ...
G06N 5/04 (2013.01); G06N 20/00 (2019.01); G16B 20/00 (2019.02); G16B 40/00 (2019.02);
Abstract

A machine learning system that implements Sobolev Independence Criterion (SIC) for feature selection is provided. The system receives a dataset including pairings of stimuli and responses. Each stimulus includes multiple features. The system generates a correctly paired sample of stimuli and responses from the dataset by pairing stimuli and responses according to the pairings of stimuli and responses in the dataset. The system generates an alternatively paired sample of stimuli and responses from the dataset by pairing stimuli and responses differently than the pairings of stimuli and responses in the dataset. The system determines a witness function and a feature importance distribution across the features that optimizes a cost function that is evaluated based on the correctly paired and alternatively paired samples of the dataset. The system selects one or more features based on the computed feature importance distribution.


Find Patent Forward Citations

Loading…