/Patent Tracker
SamsungPatent applicationAI & softwareInterest 4/10

Samsung patents method to shrink AI models using a teacher-student approach

Samsung has filed a patent for a method that reduces the size of artificial neural networks, which are the mathematical structures behind many AI features. The process uses a larger 'teacher' model to guide a smaller 'student' model, pruning unnecessary parts of the network while training it to match the teacher's output.

Why it mattersThis technique could help companies make AI features run faster and use less memory on devices like phones and laptops.

In the filing’s own words

A method of compressing an artificial neural network model includes: obtaining a first output of a to-be-compressed model by inputting training data to the to-be-compressed model and obtaining a second output of a teacher model by inputting the training data to the teacher model; obtaining a student model by pruning the to-be-compressed model using a gating network pruning network based on the first output of the to-be-compressed model; obtaining an output of the student model by inputting the training data to the student model; calculating a distillation loss based on the output of the student model and the second output of the teacher model; training the to-be-compressed model and the gating network pruning network based on the distillation loss; and obtaining a compressed model by pruning the trained to-be-compressed model with the trained gating network pruning network.

What exactly they claim (claim 1)

1. A method of compressing an artificial neural network model, the method comprising: obtaining a first output of a to-be-compressed model by inputting training data to the to-be-compressed model and obtaining a second output of a teacher model by inputting the training data to the teacher model; obtaining a student model by pruning the to-be-compressed model using a gating network pruning network based on the first output of the to-be-compressed model; obtaining an output of the student model by inputting the training data to the student model; calculating a distillation loss based on the output of the student model and the second output of the teacher model; training the to-be-compressed model and the gating network pruning network based on the distillation loss; and obtaining a compressed model by pruning the trained to-be-compressed model with the trained gating network pruning network.

Facts

Company
Samsung (SAMSUNG ELECTRONICS CO., LTD.)
Official title
METHOD AND APPARATUS WITH NEURAL NETWORK MODEL COMPRESSION
Publication number
US20260268159A1
Application number
19459474
Filed
Jan 26, 2026
Published
Sep 10, 2026
Inventors
6
Claims
20

Classified under

G06N 3/096 Physics & computingG06N 3/0495 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Samsung 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.