Efficiently Updating Connections in AI Brains
This patent describes a method for updating the connections in artificial "spiking neuron networks" more efficiently by only making changes when needed, saving computational power.
Original patent title: “Apparatus and methods for efficient updates in spiking neuron network”
This patent describes a method for updating the connections in artificial "spiking neuron networks" more efficiently by only making changes when needed, saving computational power. Granted to Qualcomm Technologies in 2016 with 27 claims and 11 forward citations, and it is expected to expire in 2032.
Coverage
What does this patent actually cover?
The patent describes a way to make artificial brains, called "spiking neuron networks," learn more efficiently. Instead of constantly updating every connection, it stores a "time history of one or more inputs" (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1) to a neuron. When an update is needed, the system determines "input-dependent connection change components (IDCC)" based on when inputs occurred and the current time (Claim 1). These components are then used to adjust "learning parameters" (like connection strengths) for that neuron. This allows updates to be done "on per neuron basis, as opposed to per-connection basis" (AbstractabstractA short summary at the front of the patent describing the invention. Not legally binding.Read more →), significantly reducing the computational work. For example, if a neuron receives several inputs in a short burst, the system can calculate the combined effect of these inputs on its connections all at once, rather than processing each connection individually at every tiny time step.
The gap
What does this patent NOT cover?
- Neural networks that are not specifically "spiking neuron networks" (ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 5).
- Update methods that always process every connection individually, rather than "on per neuron basis" (AbstractabstractA short summary at the front of the patent describing the invention. Not legally binding.Read more →).
- Updates that are performed strictly at regular time intervals without considering "on-demand" or "event-dependent" triggers (AbstractabstractA short summary at the front of the patent describing the invention. Not legally binding.Read more →, ClaimclaimA numbered sentence at the end of a patent that legally defines what the inventor owns. The most important section.Read more → 1).
- Learning parameter adjustments not based on a "time history of one or more inputs" or "input-dependent connection change components" (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 core innovation is decomposing connection updates into "event-dependent connection change components" and then applying these changes "on per neuron basis" rather than checking and updating every single connection individually. This significantly reduces the number of calculations needed, especially in large networks.
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
Neuromorphic computing chips like Intel Loihi
AI accelerators for edge devices
Low-power AI systems for IoT
Spiking neural network software frameworks
Why it matters
The bigger picture
Efficient updates are crucial for deploying artificial intelligence on devices with limited power, like smartphones or IoT sensors. By reducing the computational load for learning, this technology helps make AI more practical for "edge computing" where data is processed locally instead of in the cloud. This allows for faster responses and greater privacy in AI applications.
Filed
July 27, 2012
Granted
February 9, 2016
Market context
Who's building on this
Companies in this space
Qualcomm Technologies Inc., the assigneeassigneeThe entity that owns the patent — usually the inventor's employer or a company.Read more →, continues to develop AI hardware and software, including solutions for efficient on-device AI. Other companies active in neuromorphic computing, such as Intel and IBM, are also exploring efficient SNN architectures and learning algorithms. Startups focused on specialized AI accelerators for edge devices also build on similar principles.
Market impact
This patent addresses a core challenge in making AI practical for widespread use: computational efficiency. By enabling faster and less resource-intensive learning in spiking neural networks, it contributes to the development of low-power AI chips and systems. This helps push AI capabilities from large data centers to smaller, embedded devices, expanding the market for on-device intelligence in consumer electronics and IoT.
Claim 1 — Plain English
What this patent covers
The patent describes a way to make artificial brains, called "spiking neuron networks," learn more efficiently. Instead of constantly updating every connection, it stores a "time history of one or more inputs" (Claim 1) to a neuron. When an update is needed, the system determines "input-dependent connection change components (IDCC)" based on when inputs occurred and the current time (Claim 1). These components are then used to adjust "learning parameters" (like connection strengths) for that neuron. This allows updates to be done "on per neuron basis, as opposed to per-connection basis" (Abstract), significantly reducing the computational work. For example, if a neuron receives several inputs in a short burst, the system can calculate the combined effect of these inputs on its connections all at once, rather than processing each connection individually at every tiny time step.
The clever bit
The core innovation is decomposing connection updates into "event-dependent connection change components" and then applying these changes "on per neuron basis" rather than checking and updating every single connection individually. This significantly reduces the number of calculations needed, especially in large networks.
What it does not cover
- Neural networks that are not specifically "spiking neuron networks" (Claim 5).
- Update methods that always process every connection individually, rather than "on per neuron basis" (Abstract).
- Updates that are performed strictly at regular time intervals without considering "on-demand" or "event-dependent" triggers (Abstract, Claim 1).
- Learning parameter adjustments not based on a "time history of one or more inputs" or "input-dependent connection change components" (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
Strong
Citation count
22/40
Moderately cited
Claim breadth
18/20
Very broad protection
Recency
5/20
Granted 10–20 years ago
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
$87K – $280K
Midpoint $175K · 5.9 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
27 claims as filed with the patent office.
Concepts involved
Citations
Patent lineage
Cite this patent
Levin, J. A., Izhikevich, E., Sinyavskiy, O., & Polonichko, V. (2016). Efficiently Updating Connections in AI Brains (U.S. Patent No. 9,256,823). U.S. Patent and Trademark Office. https://patentbrief.org/patent/us/9256823/apparatus-and-methods-for-efficient-updates-in-spiking-neuron-network
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="US9256823"></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 9256215 · 2016 · Brain
How Artificial Neurons Learn from Spikes and Internal States
US 11507804 · 2022 · Commissariat a lEnergie Atomique et aux Energies Alternatives CEA
Efficient Hardware for Spiking Neural Network Calculations
US 20250363357 · Ubotica Technologies
How to Update AI on Small Devices with Slow Internet
US 11741188 · 2023 · Western Digital Technologies
How a Chip Uses Memory to Speed Up AI Calculations
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 Efficiently Updating Connections in AI Brains cover?
This patent describes a method for updating the connections in artificial "spiking neuron networks" more efficiently by only making changes when needed, saving computational power.
Who owns patent US 9256823?
Qualcomm Technologies owns this patent, granted in 2016.
When does this patent expire?
This patent is expected to expire on July 27, 2032, when the invention enters the public domain.
What is patent US 9256823 cited by?
This patent has been cited by 11 later patents that build on its ideas.
What problem does this patent solve?
Efficient updates are crucial for deploying artificial intelligence on devices with limited power, like smartphones or IoT sensors. By reducing the computational load for learning, this technology helps make AI more practical for "edge computing" where data is processed locally instead of in the cloud. This allows for faster responses and greater privacy in AI applications.
What does this patent NOT cover?
Neural networks that are not specifically "spiking neuron networks" (Claim 5).
Patent monitoring