How to Force AI to Follow Logical Rules During Training
A system that uses a dual-headed neural network to ensure AI models obey specific logical rules by embedding those rules directly into the training process.
Original patent title: “Trusted neural network system”
A system that uses a dual-headed neural network to ensure AI models obey specific logical rules by embedding those rules directly into the training process. Granted to SRI International Inc in 2023 with 22 claims and 2 forward citations.
Key facts
Coverage
What does this patent actually cover?
This system improves AI reliability by preventing models from making decisions that violate predefined logical rules. It uses a 'shared' neural network that feeds into two separate branches: a data head and a logic head. The data head focuses on learning patterns from raw data, while the logic head monitors whether those patterns violate specific logical constraints. If a violation occurs, the logic head sends an error signal back to the shared network, forcing it to adjust its internal parameters until the output satisfies the rules. For example, in a self-driving car application, this could ensure the AI never predicts a path that crosses a solid double-yellow line, regardless of what the training data suggests.
The gap
What does this patent NOT cover?
- Does not cover standard neural networks that lack a dedicated logic head for constraint enforcement.
- Does not cover post-training filtering or 'guardrail' systems that check outputs after the AI has already made a prediction.
- Does not cover systems that rely solely on massive datasets to implicitly learn constraints without explicit logical rule integration.
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
What made this novel
By treating logical constraints as a loss function that propagates error back to the shared model, the system forces the AI to treat 'breaking a rule' exactly the same way it treats 'getting an answer wrong'.
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
Autonomous vehicle path planning
Automated medical diagnosis systems
Algorithmic financial trading compliance
Why it matters
The bigger picture
As AI is deployed in high-stakes fields like healthcare, finance, and autonomous vehicles, the 'black box' nature of neural networks is a major liability. This patent provides a formal method to bake safety and compliance into the model architecture itself, rather than relying on trial-and-error training.
Filed
December 19, 2018
Granted
May 16, 2023
Market context
Who's building on this
Companies in this space
SRI International continues to research neuro-symbolic AI, which combines neural networks with symbolic logic. Major tech companies like Google, Microsoft, and IBM are actively pursuing similar 'explainable AI' (XAI) and 'constrained optimization' techniques to make deep learning models safer for enterprise use.
Market impact
This technology addresses the critical 'trust gap' in AI adoption. By providing a mathematical framework for rule-based AI, it enables industries with strict regulatory requirements to adopt machine learning models that were previously considered too unpredictable or risky for deployment.
Claim 1 — Plain English
What this patent covers
This system improves AI reliability by preventing models from making decisions that violate predefined logical rules. It uses a 'shared' neural network that feeds into two separate branches: a data head and a logic head. The data head focuses on learning patterns from raw data, while the logic head monitors whether those patterns violate specific logical constraints. If a violation occurs, the logic head sends an error signal back to the shared network, forcing it to adjust its internal parameters until the output satisfies the rules. For example, in a self-driving car application, this could ensure the AI never predicts a path that crosses a solid double-yellow line, regardless of what the training data suggests.
The clever bit
By treating logical constraints as a loss function that propagates error back to the shared model, the system forces the AI to treat 'breaking a rule' exactly the same way it treats 'getting an answer wrong'.
What it does not cover
- Does not cover standard neural networks that lack a dedicated logic head for constraint enforcement.
- Does not cover post-training filtering or 'guardrail' systems that check outputs after the AI has already made a prediction.
- Does not cover systems that rely solely on massive datasets to implicitly learn constraints without explicit logical rule integration.
Patent timeline
Application submitted to the patent office
Application published, typically 18 months after filing
Patent officially issued
PatentBrief Score
Impact Score
Moderate
Citation count
10/40
Early citations
Claim breadth
15/20
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
$62K – $200K
Midpoint $125K · 12.5 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.
The original legal language
Original claims
22 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Lincoln, P., Ghosh, S., Jha, S., & Tiwari, A. (2023). How to Force AI to Follow Logical Rules During Training (U.S. Patent No. 11,651,227). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/11651227/muzero
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="US11651227"></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
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 to Force AI to Follow Logical Rules During Training cover?
A system that uses a dual-headed neural network to ensure AI models obey specific logical rules by embedding those rules directly into the training process.
Who owns patent US 11651227?
SRI International Inc owns this patent, granted in 2023.
When does this patent expire?
This patent is expected to expire on May 16, 2043, when the invention enters the public domain.
What is patent US 11651227 cited by?
This patent has been cited by 2 later patents that build on its ideas.
What problem does this patent solve?
As AI is deployed in high-stakes fields like healthcare, finance, and autonomous vehicles, the 'black box' nature of neural networks is a major liability. This patent provides a formal method to bake safety and compliance into the model architecture itself, rather than relying on trial-and-error training.
What does this patent NOT cover?
Does not cover standard neural networks that lack a dedicated logic head for constraint enforcement.
Patent monitoring