/Patent Tracker
MicrosoftPatent applicationAI & softwareInterest 4/10

Microsoft patents neural network method that skips steps to save time

Microsoft has filed a patent for a way to make neural networks process data more efficiently. The system decides at each step whether to keep refining the data or move on to the next stage, skipping unnecessary calculations. This approach aims to reduce the time and energy needed to run these models.

Why it mattersThis could make AI applications run faster and use less power, which is important for devices like phones and laptops.

In the filing’s own words

A technique processes input information using a machine-trained model in a context-specific manner. The technique includes, for a particular processing block: receiving a set of input tokens; transforming the set of input tokens into a set of output tokens; and generating a control decision based on the output tokens. For a first state, the technique appends at least one of the output tokens to the input tokens to define a new set of input tokens and then repeats the transforming and generating operations. For a second state, the technique passes at least some of the set of output tokens to a next processing block. The token(s) passed to the next processing block convey supplemental information that does not necessarily have a verbal counterpart. The technique has the end effect of invoking transformation operations in a context-based as-needed basis, which, in turn, reduces latency and the consumption of resources.

What exactly they claim (claim 1)

1. A method for processing input information using a machine-trained model, comprising: receiving the input information; processing the input information using the machine-trained model, the machine-trained model including a series of processing blocks, a particular processing block of the series of processing blocks performing operations of: receiving a set of input tokens; transforming the set of input tokens into a set of output tokens; generating a control decision based on the output tokens, the control decision having at least two selectable states, including a first state and a second state; for the first state, appending at least one of the output tokens to the input tokens to define a new set of input tokens, and repeating the transforming and generating; and for the second state, passing at least some of the set of output tokens to a next processing block for processing.

Facts

Company
Microsoft (Microsoft Technology Licensing, LLC)
Official title
Context-Dependent Generation of Supplemental Information on a Per-Level Basis in a Neural Network
Publication number
US20260260066A1
Application number
19067898
Filed
Mar 1, 2025
Published
Sep 3, 2026
Inventors
3
Claims
20

Classified under

G06F 40/284 Physics & computing
Read the full filing (official PDF) ↗ Open in the Patent Tracker

More from Microsoft 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.