/Patent Tracker
NvidiaGranted patentAI & softwareInterest 4/10

Nvidia patents method to shrink neural network data using shared values

Patent drawing
Patent drawing from the official filing.

This patent describes a way to save storage space when handling data for neural networks. It works by finding common numbers in a group of data points and storing only the differences between them, rather than the full original numbers.

Why it mattersIt offers a specific technical method to reduce the memory footprint of AI models, which is a standard engineering goal for running software efficiently.

In the filing’s own words

Systems and methods for generating a representative value of a data set by first compressing a portion of values in the data set to determine a first common value and further compressing a subset of the portion of values to determine a second common value. The representative value is generated by taking the difference between the first common value and the second common value, wherein the representative value corresponds to a mathematical relationship between the first and second common values and each value within the subset of the portion of values. The representative value requires less storage than the first and second common values.

What exactly they claim (claim 1)

1. One or more processors, comprising: circuitry to: decompress a plurality of compressed numbers based, at least in part, on one or more relationships between a first number common to each of the plurality of compressed numbers and one or more second numbers common to each number within a subset of the plurality of compressed numbers; and store the plurality of compressed numbers in a datastore based, at least in part, on one or more indicators of the one or more relationships between the first number and the one or more second numbers.

Facts

Company
Nvidia (NVIDIA Corporation)
Official title
Data compression for a neural network
Patent number
US12748971B2
Application number
18883888
Filed
Sep 12, 2024
Granted
Sep 29, 2026
Inventors
1
Claims
20

Classified under

G06N 3/08 Physics & computingG06F 7/57 Physics & computingG06F 17/16 Physics & computingH03M 7/702 Electricity & electronics

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.