/Patent Tracker
NvidiaPatent applicationAI & softwareInterest 6/10

Nvidia patents method to speed up neural networks by sharing scale factors

Patent drawing
Patent drawing from the official filing.

Nvidia describes a way to make neural networks run faster by simplifying how they handle basic math like addition and subtraction. The method uses shared scale factors for the numbers being calculated, which allows the system to use less precise, faster math without losing accuracy.

Why it mattersThis could help make AI models run more efficiently on existing hardware, potentially lowering the power needed for tasks like image recognition or language processing.

In the filing’s own words

Neural networks, and in particular deep neural networks, are traditionally resource intensive as they require execution of a significant number of computations in order to generate an output. In an effort to accelerate neural networks, quantization has been employed in which the input/output of certain operations are scaled. However, the degree to which a neural network can be quantized is limited because current scaling methods, which do not ensure consistent scaling for operands, cannot be applied to the commonly used element-wise operations (e.g. addition and subtraction). The present disclosure provides scaling of element-wise operations in a neural network by using scale factors that are shared between operands, thus allowing for greater quantization of neural networks.

What exactly they claim (claim 1)

1. A method, comprising: at a device: determining one or more scale factors to be used for an element-wise operation of a neural network; scaling operands to the element-wise operation by the one or more scale factors to form scaled operands; performing the element-wise operation on the scaled operands to generate a scaled output.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
SCALING ELEMENT-WISE OPERATIONS OF A NEURAL NETWORK
Publication number
US20260300712A1
Application number
19091697
Filed
Mar 26, 2025
Published
Oct 1, 2026
Inventors
3
Claims
33

Classified under

G06N 3/08 Physics & computingG06N 5/04 Physics & computing

More from Nvidia in AI & software

Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.