How AI Designs Its Own Brains: Hierarchical Neural Architecture Search
This patent describes a computer method for automatically designing neural networks by representing their structures as multi-level graphs and evolving the best designs based on how well they perform.
Original patent title: “Using hierarchical representations for neural network architecture searching”
This patent describes a computer method for automatically designing neural networks by representing their structures as multi-level graphs and evolving the best designs based on how well they perform. Granted to GDM Holding in 2026 with 20 claims, and it is expected to expire in 2044.
Coverage
What does this patent actually cover?
The patent describes a computer-implemented method for automatically finding the best design, or "architecture," for a neural network. It does this by representing a neural network's structure as a "hierarchical set of graphs" (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1). Think of these graphs as blueprints with different levels of detail. At the lowest level, the graphs use basic "primitive neural network operations" like simple calculations or connections (Claim 1, 2, 3). Higher levels build more complex operations by combining these simpler graphs. The method then creates a group of sample neural network designs, trains them, and measures how well they perform using a "fitness value" (Claim 1). It then selects the best-performing designs and can even "mutate" them, meaning it makes small changes to create new, potentially better designs, and repeats the process (Claim 8). For example, it might try different combinations of convolutional operations (Claim 3) or even no-connection operations (Claim 5) between nodes to see which arrangement yields the highest fitness.
The gap
What does this patent NOT cover?
- Does not cover manual design of neural network architectures by human experts.
- Does not cover methods for determining architectures that do not use a hierarchical graph representation.
- Does not cover methods that evaluate architectures without determining a "fitness value" (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
- Does not cover methods that do not involve "generating data defining a hierarchical set of graphs" (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
- Does not cover methods where the operations for higher-level graphs are not selected from preceding hierarchical levels (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The noveltynoveltyThe requirement that an invention be different from anything publicly known before its priority date.Read more → lies in using a "hierarchical set of graphs" to represent neural network architectures, where complex operations are built recursively from simpler ones. This structured representation allows for systematic exploration and evolution of designs, making the search for optimal architectures more efficient and scalable than flat representations.
The Patent Drawing
Schematic visualization of the patent's claim structure. Hand-drawn diagrams in progress for each landmark patent.
Where you've seen this
Real-world examples
Automated Machine Learning (AutoML) platforms
Neural Architecture Search (NAS) tools
AI model development for computer vision
AI model development for natural language processing
Why it matters
The bigger picture
Designing effective neural networks is incredibly complex and time-consuming for humans. This patent addresses that challenge by automating the process, allowing computers to discover novel and efficient architectures that might be difficult for human experts to conceive. This automation can accelerate advancements in artificial intelligence, making powerful AI models more accessible and faster to develop for various applications.
Filed
January 17, 2024
Granted
May 19, 2026
Market context
Who's building on this
Companies in this space
Companies like Google (DeepMind, Google Brain), Microsoft, and various AI startups are actively researching and developing advanced Neural Architecture Search (NAS) techniques. These organizations continuously seek more efficient ways to design and optimize AI models for various applications, from cloud services to edge devices.
Market impact
This type of technology significantly impacts the AI development market by democratizing access to high-performing neural networks. It reduces the need for extensive manual expert tuning, potentially lowering development costs and accelerating the deployment of AI solutions across industries. It enables the creation of more specialized and efficient AI models for specific tasks, fostering innovation in areas like computer vision and natural language processing.
Claim 1 — Plain English
What this patent covers
The patent describes a computer-implemented method for automatically finding the best design, or "architecture," for a neural network. It does this by representing a neural network's structure as a "hierarchical set of graphs" (Claim 1). Think of these graphs as blueprints with different levels of detail. At the lowest level, the graphs use basic "primitive neural network operations" like simple calculations or connections (Claim 1, 2, 3). Higher levels build more complex operations by combining these simpler graphs. The method then creates a group of sample neural network designs, trains them, and measures how well they perform using a "fitness value" (Claim 1). It then selects the best-performing designs and can even "mutate" them, meaning it makes small changes to create new, potentially better designs, and repeats the process (Claim 8). For example, it might try different combinations of convolutional operations (Claim 3) or even no-connection operations (Claim 5) between nodes to see which arrangement yields the highest fitness.
The clever bit
The novelty lies in using a "hierarchical set of graphs" to represent neural network architectures, where complex operations are built recursively from simpler ones. This structured representation allows for systematic exploration and evolution of designs, making the search for optimal architectures more efficient and scalable than flat representations.
What it does not cover
- Does not cover manual design of neural network architectures by human experts.
- Does not cover methods for determining architectures that do not use a hierarchical graph representation.
- Does not cover methods that evaluate architectures without determining a "fitness value" (Claim 1).
- Does not cover methods that do not involve "generating data defining a hierarchical set of graphs" (Claim 1).
- Does not cover methods where the operations for higher-level graphs are not selected from preceding hierarchical levels (Claim 1).
Patent timeline
Application submitted to the patent office
Application published, typically 18 months after filing
Patent officially issued
Patent enters public domain
PatentBrief Score
Impact Score
Early stage
Citation count
0/40
No citations yet
Claim breadth
13/20
Broad claimsclaimsThe numbered statements at the end of a patent that legally define what the inventor owns.Read more →
Recency
20/20
Granted within 5 years
Assignee scale
0/20
Independent or smaller assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →
PatentBrief Impact Score — based on citation count, claim breadth, recency, and assignee scale. Not a legal assessment.
Heuristic Value Estimate
What this patent might be worth
$31K – $100K
Midpoint $62K · 17.3 yr remaining · industry ×1.6
Heuristic only — blends forward/backward citation counts, claim scope, time remaining, litigation history, and CPC-derived industry baseline. Real valuations need a professional appraisal.
Claim text not yet imported for this patent
The original legal language
Original claims
20 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Vinyals, O., Liu, H., Simonyan, K., Kavukcuoglu, K., & Fernando, C. T. (2026). How AI Designs Its Own Brains: Hierarchical Neural Architecture Search (U.S. Patent No. 12,632,737). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/12632737/using-hierarchical-representations-for-neural-network-architecture-searching
Auto-generated from the patent record. Double-check author order and the issue date against the official USPTO document before submitting.
Embed
Add this patent to your site
Drop this plain-English patent card into any blog post or article — free, no signup. It always links back to the full breakdown here.
<div data-patentlens-widget data-patent-number="US12632737"></div> <script src="https://patentbrief.org/embed.js" async></script>
Stay in the loop
Get a weekly digest of new patents.
One email per week. No spam. Unsubscribe anytime.
Keep exploring
Related patents you should know
US 4683195 · 1987
How to Make Billions of Copies of a DNA Segment
This patent describes the Polymerase Chain Reaction (PCR), a method to rapidly create many copies of a specific piece of DNA or RNA, enabling its detection and analysis.
Cetus Corp
US 8697359 · 2014
How to Edit Genes in Human Cells Using an Engineered CRISPR System
This patent describes an engineered CRISPR-Cas9 system for precisely cutting DNA in eukaryotic cells to change how genes work, opening the door for gene editing in complex organisms.
Massachusetts Institute of Technology
US 7657849 · 2010
How the iPhone's Slide-to-Unlock Gesture Works
Apple's 2010 patent describes unlocking a device by dragging a specific graphical image across the touchscreen along a predefined path, a gesture that became iconic with the original iPhone.
Apple Inc
US 4733665 · 1988
How Doctors Implant a Permanent Stent Using a Balloon
This patent describes the method for placing a permanent, expandable wire mesh tube inside a blood vessel or other body tube using a balloon-tipped catheter to widen it and keep it open.
Expandable Grafts Partnership
US 4965188 · 1990
How to Make Many Copies of a DNA Piece with Heat
This patent describes the Polymerase Chain Reaction (PCR) method, a technique to make millions of copies of a specific DNA segment using a heat-resistant enzyme and repeated temperature changes.
Cetus Corp
US 4235871 · 1980
How to Encapsulate Active Materials in Lipid Bubbles Efficiently
This patent describes a method for trapping biologically active substances inside tiny, multi-layered fat bubbles called liposomes, using a specific water-in-oil emulsion and gel-forming process to improve how much material gets captured.
Individual
Semantically similar
You might also find these interesting
US 11501192 · 2022 · University of Toronto
How to Automatically Tune Machine Learning Settings Using Smart Math
US 20230162023 · Mitsubishi Electric Research Laboratories
Automated AI for Adapting to New Data Without Retraining
US 10832138 · 2020 · Samsung Electronics Co Ltd
How to Automatically Expand Neural Networks by Adding New Nodes
US 20250371349 · Intel
How AI Learns to Run Faster on Specific Computer Chips
More to explore
More in AI & Machine Learning
US 10452978 · 2019 · Google LLC
How AI Models Understand Language Using 'Attention'
US 6523026 · 2003 · Huntsman International LLC
How Computers Find Hidden Connections Between Different Fields of Knowledge
US 11615208 · 2023 · Capital One Services LLC
How Cloud Systems Automatically Create and Train AI Data Models
US 10402750 · 2019 · Facebook Inc
How Facebook Uses Deep Learning to Predict What You Might Like
New to patents?
Common Questions
Frequently Asked Questions
What does How AI Designs Its Own Brains: Hierarchical Neural Architecture Search cover?
This patent describes a computer method for automatically designing neural networks by representing their structures as multi-level graphs and evolving the best designs based on how well they perform.
Who owns patent US 12632737?
GDM Holding owns this patent, granted in 2026.
When does this patent expire?
This patent is expected to expire on January 17, 2044, when the invention enters the public domain.
What problem does this patent solve?
Designing effective neural networks is incredibly complex and time-consuming for humans. This patent addresses that challenge by automating the process, allowing computers to discover novel and efficient architectures that might be difficult for human experts to conceive. This automation can accelerate advancements in artificial intelligence, making powerful AI models more accessible and faster to develop for various applications.
What does this patent NOT cover?
Does not cover manual design of neural network architectures by human experts.
Same assignee
More from GDM Holding
Patent monitoring