Information processing device for improving quality of generator of GAN
Summary
The USPTO granted patent US12596910B2 to Nomura Research Institute, Ltd. covering an information processing device that executes learning algorithms for conditional generative adversarial networks and formal verification algorithms to ensure generative models produce outputs within designated class boundaries. The patent addresses GAN quality improvement through classification-based property verification within defined noise vector norms.
What changed
The USPTO issued patent US12596910B2 to Nomura Research Institute, Ltd. for an information processing device that improves the quality of generators in generative adversarial networks. The device executes three main functions: learning a conditional GAN generative model, learning a classification model to verify output class membership, and determining whether generated outputs satisfy specified properties using formal verification algorithms. The patent claims ensure the generative model does not output data classified into incorrect classes within defined noise vector ranges.
Technology companies developing generative AI systems should monitor this patent for potential licensing considerations and competitive landscape awareness. The formal verification approach for GAN quality assurance represents a technical methodology that may inform internal R&D strategies and compliance with AI governance frameworks.
What to do next
- Monitor patent portfolio for competitive analysis
- Review for freedom-to-operate considerations
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.
Information processing device for improving quality of generator of generative adversarial network (GAN)
Grant US12596910B2 Kind: B2 Apr 07, 2026
Assignee
NOMURA RESEARCH INSTITUTE, LTD.
Inventors
Teruhiro Tagomori
Abstract
An information processing device executes learning a generative model that generates data belonging to a designated class on the basis of a noise vector and the designated class by executing a learning algorithm of a conditional generative adversarial network, learning a classification model that classifies input data based on whether the input data is in the designated class, and determining whether a property is satisfied when the classification model classifies an output of the generative model by executing a formal verification algorithm. The property indicates that the generative model does not generate data classified into a class different from a first class designated for the generative model, within a range of a certain norm of a noise vector input to the generative model.
CPC Classifications
G06N 3/045 G06N 3/094 G06N 3/09 G06N 3/048 G06N 3/0475 G06N 3/0464 G06F 18/217 G06F 18/2431 G06F 18/24
Filing Date
2022-08-03
Application No.
17880336
Claims
5
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 summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
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.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.