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:
Mar. 03, 2026

Filed:

Jan. 14, 2021
Applicant:

Red Hat, Inc., Raleigh, NC (US);

Inventors:

Mark Kurtz, Medford, MA (US);

Dan Alistarh, Meyrin, CH;

Assignee:

Red Hat, Inc., Raleigh, NC (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06N 3/082 (2023.01); G06F 17/16 (2006.01); G06N 3/047 (2023.01);
U.S. Cl.
CPC ...
G06N 3/082 (2013.01); G06F 17/16 (2013.01); G06N 3/047 (2023.01);
Abstract

A system and a method of training a Neural network (NN) model may include, receiving a pretrained NN model, that may include a plurality of layers, each associated with an activation matrix; selecting at least one, and performing an iterative training process on the layer. The iterative training process may include, applying an activation threshold to the activation matrix of the layer; measuring an accuracy value of the NN model; retraining the layer, while using a bimodal regularization function of one or more activation matrices of the NN model; and repeating the applying, measuring and retraining, while each repetition uses different activation threshold values. This repetition may be repeated until a maximal value of the activation threshold, where the NN model still converges, is found.


Find Patent Forward Citations

Kurtz, Mark. (2026). System and method of training a neural network (U.S. Patent No. 12566958). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12566958

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

Loading…