/Patent Tracker
SamsungGranted patentAI & softwareInterest 6/10

Samsung patents neural network that adjusts accuracy to save power

Patent drawing
Patent drawing from the official filing.

This filing describes a method for running artificial intelligence models on devices like phones. It allows the system to stop processing early if a quick, rough answer is good enough, or continue to a deeper level for a precise result based on available time and memory.

Why it mattersThis technique could help smartphones and other gadgets run smart features faster and with less battery drain by only using the computing power they actually need.

In the filing’s own words

Disclosed is an electronic apparatus. The electronic apparatus includes a memory storing at least one instruction, and a processor coupled to the memory and configured to control the electronic apparatus, the processor configured to identify one of a plurality of exit points included in a neural network based on at least one constraint in at least one of processing or the electronic apparatus, process the input data via the neural network and obtain processing results output from the identified exit point as output data.

What exactly they claim (claim 1)

1. A method for controlling an electronic apparatus, the method comprising: receiving input data; identifying one of a plurality of exit points included in a neural network based on a time taken to reach each exit point to provide a processing result and based on a memory capacity of the electronic apparatus, the neural network providing progressive hierarchical inference by having at least a coarse-grained domain and a fine-grained domain, and coarse-grained results output from exit points in the coarse-grained domain are further processed in the fine-grained domain to obtain fine-grained results; processing the input data via the neural network; obtaining processing results output from the identified exit point as output data; and using knowledge distillation, jointly training a plurality of classifiers corresponding to the plurality of exit points.

Facts

Company
Samsung (SAMSUNG ELECTRONICS CO., LTD.)
Official title
Method and system for implementing a variable accuracy neural network
Patent number
US12755136B2
Application number
16923447
Filed
Jul 8, 2020
Granted
Oct 6, 2026
Inventors
3
Claims
17

Classified under

G06N 3/063 Physics & computingG06N 3/04 Physics & computing

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.