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:
Apr. 14, 2025

Filed:

Oct. 25, 2023
Applicant:

Capital One Services, Llc, McLean, VA (US);

Inventors:

Austin Walters, Savoy, IL (US);

Vincent Pham, Champaign, IL (US);

Galen Rafferty, Mahomet, IL (US);

Anh Truong, Champaign, IL (US);

Mark Watson, Urbana, IL (US);

Jeremy Goodsitt, Champaign, IL (US);

Assignee:

Capital One Services, LLC, McLean, VA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 20/00 (2018.12); G06F 8/71 (2017.12); G06F 9/54 (2005.12); G06F 11/3604 (2024.12); G06F 11/362 (2024.12); G06F 16/22 (2018.12); G06F 16/242 (2018.12); G06F 16/2455 (2018.12); G06F 16/248 (2018.12); G06F 16/25 (2018.12); G06F 16/28 (2018.12); G06F 16/335 (2018.12); G06F 16/903 (2018.12); G06F 16/9032 (2018.12); G06F 16/9038 (2018.12); G06F 16/906 (2018.12); G06F 16/93 (2018.12); G06F 17/15 (2005.12); G06F 17/16 (2005.12); G06F 17/18 (2005.12); G06F 18/20 (2022.12); G06F 18/21 (2022.12); G06F 18/2115 (2022.12); G06F 18/214 (2022.12); G06F 18/22 (2022.12); G06F 18/23 (2022.12); G06F 18/24 (2022.12); G06F 18/2411 (2022.12); G06F 18/2415 (2022.12); G06F 18/40 (2022.12); G06F 21/55 (2012.12); G06F 21/60 (2012.12); G06F 21/62 (2012.12); G06F 30/20 (2019.12); G06F 40/117 (2019.12); G06F 40/166 (2019.12); G06F 40/20 (2019.12); G06N 3/04 (2022.12); G06N 3/044 (2022.12); G06N 3/045 (2022.12); G06N 3/06 (2005.12); G06N 3/08 (2022.12); G06N 3/088 (2022.12); G06N 3/094 (2022.12); G06N 5/00 (2022.12); G06N 5/02 (2022.12); G06N 5/04 (2022.12); G06N 7/00 (2022.12); G06N 7/01 (2022.12); G06Q 10/04 (2022.12); G06T 7/194 (2016.12); G06T 7/246 (2016.12); G06T 7/254 (2016.12); G06T 11/00 (2005.12); G06V 10/70 (2021.12); G06V 10/98 (2021.12); G06V 30/194 (2021.12); G06V 30/196 (2021.12); H04L 9/40 (2021.12); H04L 67/00 (2021.12); H04L 67/306 (2021.12); H04N 21/234 (2010.12); H04N 21/81 (2010.12);
U.S. Cl.
CPC ...
G06F 9/541 (2012.12); G06F 8/71 (2012.12); G06F 9/54 (2012.12); G06F 9/547 (2012.12); G06F 11/3608 (2012.12); G06F 11/3628 (2012.12); G06F 11/3636 (2012.12); G06F 16/2237 (2018.12); G06F 16/2264 (2018.12); G06F 16/2423 (2018.12); G06F 16/24568 (2018.12); G06F 16/248 (2018.12); G06F 16/254 (2018.12); G06F 16/258 (2018.12); G06F 16/283 (2018.12); G06F 16/285 (2018.12); G06F 16/288 (2018.12); G06F 16/335 (2018.12); G06F 16/90332 (2018.12); G06F 16/90335 (2018.12); G06F 16/9038 (2018.12); G06F 16/906 (2018.12); G06F 16/93 (2018.12); G06F 17/15 (2012.12); G06F 17/16 (2012.12); G06F 17/18 (2012.12); G06F 18/2115 (2022.12); G06F 18/214 (2022.12); G06F 18/2148 (2022.12); G06F 18/217 (2022.12); G06F 18/2193 (2022.12); G06F 18/22 (2022.12); G06F 18/23 (2022.12); G06F 18/24 (2022.12); G06F 18/2411 (2022.12); G06F 18/2415 (2022.12); G06F 18/285 (2022.12); G06F 18/40 (2022.12); G06F 21/552 (2012.12); G06F 21/60 (2012.12); G06F 21/6245 (2012.12); G06F 21/6254 (2012.12); G06F 30/20 (2019.12); G06F 40/117 (2019.12); G06F 40/166 (2019.12); G06F 40/20 (2019.12); G06N 3/04 (2012.12); G06N 3/044 (2022.12); G06N 3/045 (2022.12); G06N 3/06 (2012.12); G06N 3/08 (2012.12); G06N 3/088 (2012.12); G06N 3/094 (2022.12); G06N 5/00 (2012.12); G06N 5/02 (2012.12); G06N 5/04 (2012.12); G06N 7/00 (2012.12); G06N 7/01 (2022.12); G06N 20/00 (2018.12); G06Q 10/04 (2012.12); G06T 7/194 (2016.12); G06T 7/246 (2016.12); G06T 7/248 (2016.12); G06T 7/254 (2016.12); G06T 11/001 (2012.12); G06V 10/768 (2021.12); G06V 10/993 (2021.12); G06V 30/194 (2021.12); G06V 30/1985 (2021.12); H04L 63/1416 (2012.12); H04L 63/1491 (2012.12); H04L 67/306 (2012.12); H04L 67/34 (2012.12); H04N 21/23412 (2012.12); H04N 21/8153 (2012.12); G06T 2207/10016 (2012.12); G06T 2207/20081 (2012.12); G06T 2207/20084 (2012.12);
Abstract

Systems and methods for determining neural network brittleness are disclosed. For example, the system may include one or more memory units storing instructions and one or more processors configured to execute the instructions to perform operations. The operations may include receiving a modeling request comprising a preliminary model and a dataset. The operations may include determining a preliminary brittleness score of the preliminary model. The operations may include identifying a reference model and determining a reference brittleness score of the reference model. The operations may include comparing the preliminary brittleness score to the reference brittleness score and generating a preferred model based on the comparison. The operations may include providing the preferred model.


Find Patent Forward Citations

Loading…