How AI Learns to Run Faster on Specific Computer Chips
This patent describes how a smart AI system, called a reinforcement learning agent, trains other AI models to run more efficiently on specific computer hardware by cleverly reducing their size without losing too much accuracy.
Original patent title: “Methods and apparatus for hardware-aware machine learning model training”
This patent describes how a smart AI system, called a reinforcement learning agent, trains other AI models to run more efficiently on specific computer hardware by cleverly reducing their size without losing too much accuracy. Owned by Intel with 23 claims and 2 forward citations, and it is expected to expire in 2045.
Coverage
What does this patent actually cover?
The patent details a method for optimizing neural networks to run efficiently on a specific hardware device. It uses a "reinforcement learning agent" (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1) that receives an "embedding state" (Claim 1) representing characteristics of a neural network layer, such as its "kernel size" or "number of weights" (Claim 4). Based on this information, the agent generates "actions" (Claim 1) to reduce the "computational cycles" (Claim 1) needed to execute the neural network. A common action is "pruning weights" (Claim 2) within the layer, determined by a "sparsity ratio" (Claim 2). After the modified neural network runs, the system determines a "reward" (Claim 1) for the agent by checking if the output's "accuracy" (Claim 1) meets a set threshold and if a "target cycle reduction" (Claim 6) was achieved. This reward then helps the agent update its "policy" (Claim 1) to make better optimization decisions in the future. For example, an AI model designed to detect objects in a security camera feed could be optimized this way to run quickly on the camera's embedded processor without missing important events.
The gap
What does this patent NOT cover?
- Optimizing neural networks using methods that do not involve a reinforcement learning agent to generate actions.
- Training neural networks without specifically considering the reduction of computational cycles on a target hardware device.
- Pruning weights in a neural network without evaluating the impact on both accuracy and computational cycles as part of a reward system.
- Optimization techniques that focus solely on improving neural network accuracy without also aiming to reduce execution time.
- Manual optimization of neural network layers by a human engineer without an automated learning agent.
These exclusions are unique to PatentBrief — derived from the actual claim language, not patent-office boilerplate.
Key facts
What made this novel
The innovation lies in using a reinforcement learning agent to intelligently *learn* how to optimize a neural network for a specific hardware's performance, rather than relying on fixed rules or manual tuning. This agent dynamically balances the trade-off between the model's accuracy and its computational cost on the target device.
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
AI models running on smartphone processors
Machine learning inference on embedded systems in smart home devices
Neural networks deployed on edge AI accelerators
Computer vision tasks on autonomous vehicle hardware
Optimized AI for industrial IoT sensors
Why it matters
The bigger picture
As AI models become more complex, they demand significant computing power. This patent addresses the critical challenge of deploying these models on devices with limited resources, like smartphones, drones, or IoT sensors. By automatically making AI models smaller and faster for specific hardware, it enables more widespread and efficient use of artificial intelligence outside of large data centers. This is crucial for real-time applications and reducing energy consumption.
Filed
August 21, 2025
Market context
Who's building on this
Companies in this space
Intel, the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, is a major player in developing hardware and software for AI, including specialized AI accelerators and processors. Companies like NVIDIA, Qualcomm, and ARM are also actively working on optimizing AI models for their respective hardware platforms, often using similar principles of hardware-aware optimization. Startups focused on efficient AI deployment and model compression also operate in this space.
Market impact
This type of technology is essential for the proliferation of AI into edge devices, creating a competitive advantage for hardware manufacturers who can offer more efficient AI inference. It drives innovation in both chip design and AI software frameworks, enabling new product categories that rely on low-power, high-performance AI. It also influences the development of AI model architectures that are inherently more amenable to hardware-aware optimization.
Claim 1 — Plain English
What this patent covers
The patent details a method for optimizing neural networks to run efficiently on a specific hardware device. It uses a "reinforcement learning agent" (Claim 1) that receives an "embedding state" (Claim 1) representing characteristics of a neural network layer, such as its "kernel size" or "number of weights" (Claim 4). Based on this information, the agent generates "actions" (Claim 1) to reduce the "computational cycles" (Claim 1) needed to execute the neural network. A common action is "pruning weights" (Claim 2) within the layer, determined by a "sparsity ratio" (Claim 2). After the modified neural network runs, the system determines a "reward" (Claim 1) for the agent by checking if the output's "accuracy" (Claim 1) meets a set threshold and if a "target cycle reduction" (Claim 6) was achieved. This reward then helps the agent update its "policy" (Claim 1) to make better optimization decisions in the future. For example, an AI model designed to detect objects in a security camera feed could be optimized this way to run quickly on the camera's embedded processor without missing important events.
The clever bit
The innovation lies in using a reinforcement learning agent to intelligently *learn* how to optimize a neural network for a specific hardware's performance, rather than relying on fixed rules or manual tuning. This agent dynamically balances the trade-off between the model's accuracy and its computational cost on the target device.
What it does not cover
- Optimizing neural networks using methods that do not involve a reinforcement learning agent to generate actions.
- Training neural networks without specifically considering the reduction of computational cycles on a target hardware device.
- Pruning weights in a neural network without evaluating the impact on both accuracy and computational cycles as part of a reward system.
- Optimization techniques that focus solely on improving neural network accuracy without also aiming to reduce execution time.
- Manual optimization of neural network layers by a human engineer without an automated learning agent.
Patent timeline
Application submitted to the patent office
Patent enters public domain
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
0/20
Older than 20 years
Assignee scale
20/20
Major company or institution
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 · 19.0 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
23 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Xu, X., Biro, Z., & Brick, C. How AI Learns to Run Faster on Specific Computer Chips (U.S. Patent No. 20,250,371,349). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/20250371349/methods-and-apparatus-for-hardware-aware-machine-learning-model-training
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="US20250371349"></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 20250363357 · Ubotica Technologies
How to Update AI on Small Devices with Slow Internet
US 11429864 · 2022 · Moffett International Co Ltd Hong Kong
Making Neural Networks Faster by Skipping Unnecessary Calculations
US 20220383078 · Huawei Technologies Co
Adapting AI Models to Fit Device Resources
US 10832138 · 2020 · Samsung Electronics Co Ltd
How to Automatically Expand Neural Networks by Adding New Nodes
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 Learns to Run Faster on Specific Computer Chips cover?
This patent describes how a smart AI system, called a reinforcement learning agent, trains other AI models to run more efficiently on specific computer hardware by cleverly reducing their size without losing too much accuracy.
Who owns patent US 20250371349?
This patent is owned by Intel.
When does this patent expire?
This patent is expected to expire on August 21, 2045, when the invention enters the public domain.
What is patent US 20250371349 cited by?
This patent has been cited by 2 later patents that build on its ideas.
What problem does this patent solve?
As AI models become more complex, they demand significant computing power. This patent addresses the critical challenge of deploying these models on devices with limited resources, like smartphones, drones, or IoT sensors. By automatically making AI models smaller and faster for specific hardware, it enables more widespread and efficient use of artificial intelligence outside of large data centers. This is crucial for real-time applications and reducing energy consumption.
What does this patent NOT cover?
Optimizing neural networks using methods that do not involve a reinforcement learning agent to generate actions.
Same assignee
More from Intel
Patent monitoring