Nvidia patents method for training image classifiers using object behavior
Nvidia describes a way to train neural networks to identify objects in images. The method groups training data based on how objects behave within those images to improve classification accuracy.
In the filing’s own words
Apparatuses, systems, and techniques to train neural networks to perform classification. In at least one embodiment, one or more neural networks are trained to perform classification based, at least in part, on grouping one or more sets of neural network training data according to behaviors of one or more objects within one or more images represented by the training data.
What exactly they claim (claim 1)
1. (canceled)
Facts
- Company
- Nvidia (NVIDIA Corporation)
- Official title
- TECHNIQUES FOR CLASSIFICATION WITH NEURAL NETWORKS
- Publication number
- US20260320156A1
- Application number
- 19546085
- Filed
- Feb 20, 2026
- Published
- Oct 15, 2026
- Inventors
- 4
- Claims
- 21
Classified under
G06F 18/2148 Physics & computingG06F 18/22 Physics & computingG06F 18/23 Physics & computingG06N 3/08 Physics & computingG06T 15/005 Physics & computingMore from Nvidia in AI & software
- Nvidia patents AI coach that analyzes your gameplay to suggest strategies Oct 13, 2026
- Nvidia patents AI system that writes and voices character conversations Sep 10, 2026
- Nvidia patents system that uses AI to find bugs in game videos Sep 17, 2026
- Nvidia patents AI method to make digital characters move realistically Sep 8, 2026
- Nvidia patents AI system that builds image generators from text prompts Sep 15, 2026
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.