Single-stage model training for neural architecture search
Summary
The USPTO granted US Patent No. 12596925B2 to Google LLC on April 7, 2026, covering methods for single-stage neural architecture search training. The patent contains 20 claims and relates to selecting neural networks for machine learning tasks while satisfying specified constraints.
What changed
The USPTO issued a utility patent grant to Google LLC for neural architecture search training methods. The patent covers systems and computer programs for selecting neural networks to perform machine learning tasks under constraint sets. The filing was submitted on March 5, 2021, under Application No. 17613773.
Technology companies developing AI/ML systems, neural network architectures, or automated model training pipelines should monitor this IP portfolio for potential licensing considerations or design-around opportunities. The patent's broad claim scope in neural architecture search may affect competitive positioning in AutoML and model optimization spaces.
What to do next
- Monitor for updates
Archived snapshot
Apr 7, 2026GovPing 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.
Single-stage model training for neural architecture search
Grant US12596925B2 Kind: B2 Apr 07, 2026
Assignee
Google LLC
Inventors
Jiahui Yu, Pengchong Jin, Hanxiao Liu, Gabriel Mintzer Bender, Pieter-Jan Kindermans, Mingxing Tan, Xiaodan Song, Ruoming Pang, Quoc V. Le
Abstract
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for selecting a neural network to perform a particular machine learning task while satisfying a set of constraints.
CPC Classifications
G06N 3/08 G06N 3/045 G06N 3/084 G06N 3/086 G06N 3/0985 G06N 3/082
Filing Date
2021-03-05
Application No.
17613773
Claims
20
Related changes
Get daily alerts for USPTO Patent Grants - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
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.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Grants - AI & Computing (G06N) publishes new changes.