Changeflow GovPing Telecom & Technology Method and apparatus with neural network control
Routine Notice Added Final

Method and apparatus with neural network control

Favicon for changeflow.com ChangeBridge: Patent Grants - AI & Computing (G06N)
Published
Detected
Email

Summary

The USPTO granted Samsung Electronics Patent US12596911B2 on April 7, 2026, covering a method for selecting neural networks from available networks based on minimizing the sum of mutual information between selected networks, with the networks configured to perform inference on input data. The patent names Jongseok Kim, Hyun Oh Song, and Yeonwoo Jeong as inventors and was filed under Application No. 17979962.

What changed

Samsung Electronics Co., Ltd. received USPTO Patent US12596911B2, which protects a method for selecting neural networks based on minimal mutual information between networks, configuring available neural networks for inference on input data. The patent covers CPC classifications G06N 3/04, G06N 3/045, G06N 3/063, G06N 3/08, and G06N 3/084.

The grant provides Samsung with exclusive intellectual property rights to this neural network optimization technology in the United States, which may affect competitors developing AI/ML inference optimization methods. Companies in the AI and semiconductor sectors should review this patent when designing neural network selection systems to assess potential licensing or design-around needs.

What to do next

  1. Monitor for updates

Archived snapshot

Apr 7, 2026

GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.

← USPTO Patent Grants

Method and apparatus with neural network control

Grant US12596911B2 Kind: B2 Apr 07, 2026

Assignee

Samsung Electronics Co., Ltd.

Inventors

Jongseok Kim, Hyun Oh Song, Yeonwoo Jeong

Abstract

A method and apparatus with neural network control are provided. In one general aspect, a method is performed by at least one processor of an apparatus, the method includes selecting neural networks from among available neural networks with respective input image resolutions, including plural resolutions, wherein the selected neural networks are selected based on a sum of amounts of mutual information between the selected neural networks being minimal and based on a limiting condition of a use of the available neural networks, and configuring the available neural networks to perform an inference on input data, wherein the configuring is based on the combination of the selected neural networks.

CPC Classifications

G06N 3/04 G06N 3/045 G06N 3/063 G06N 3/08 G06N 3/084

Filing Date

2022-11-03

Application No.

17979962

Claims

23

View original document →

Get daily alerts for ChangeBridge: Patent Grants - AI & Computing (G06N)

Daily digest delivered to your inbox.

Free. Unsubscribe anytime.

About this page

What is GovPing?

Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission

What's from the agency?

Source document text, dates, docket IDs, and authority are extracted directly from Samsung.

What's AI-generated?

The plain-English summary, classification, and "what to do next" steps are AI-generated from the original text. Cite the source document, not the AI analysis.

Last updated

Classification

Agency
Samsung
Published
April 7th, 2026
Instrument
Notice
Legal weight
Binding
Stage
Final
Change scope
Minor
Document ID
US12596911B2

Who this affects

Applies to
Technology companies
Industry sector
5112 Software & Technology
Activity scope
Patent granting Neural network development AI inference optimization
Geographic scope
United States US

Taxonomy

Primary area
Intellectual Property
Operational domain
Legal
Topics
Artificial Intelligence

Get alerts for this source

We'll email you when ChangeBridge: Patent Grants - AI & Computing (G06N) publishes new changes.

Optional. Personalizes your daily digest.

Free. Unsubscribe anytime.