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:
Nov. 17, 2026

Filed:

Sep. 06, 2021
Applicant:

Deutsche Telekom Ag., Bonn, DE;

Inventors:

Sebastian Fischer, Berlin, DE;

Ronald Fromm, Berlin, DE;

Amit Hacmon, Beer Sheva, IL;

Yuval Elovici, Arugot, IL;

Asaf Shabtai, Hulda, IL;

Edita Grolman, Beer Sheva, IL;

Oleg Brodt, Beer Sheva, IL;

Assignee:
Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06F 18/21 (2023.01); G06F 18/214 (2023.01); G06N 3/088 (2023.01);
U.S. Cl.
CPC ...
G06F 18/217 (2023.01); G06F 18/214 (2023.01); G06N 3/088 (2013.01);
Abstract

A system for bias estimation in Artificial Intelligence (AI) models using a pre-trained unsupervised deep neural network, comprising a bias vector generator implemented by at least one processor that executes an unsupervised DNN with a predetermined loss function. The bias vector generator is adapted to store a given ML model to be examined, with predetermined features; store a test-set of one or more test data samples being input data samples; receive a feature vector consisting of one or more input samples; output a bias vector indicating the degree of bias for each feature, according to said one or more input samples. The system also comprises a post-processor which is adapted to receive a set of bias vectors generated by said bias vector generator; process said bias vectors; calculate a bias estimation for every feature of said ML model, based on predictions of said ML model; provide a final bias estimation for each examined feature.


Find Patent Forward Citations

Quick Actions:

Fischer, Sebastian. (2026). System and a method for bias estimation in artificial intelligence (ai) models using deep neural network (U.S. Patent No. 12801697). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12801697

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…