Electronic Device, Terminal, and Operating Method with Neural Network Lightweighting
Summary
Samsung Electronics Co., Ltd. filed patent application US20260093989A1 for an electronic device and operating method that generates candidate neural networks by excluding nonlinear layers, selects candidates based on importance and latency values, and merges successive convolution layers. The patent (Application No. 19329970) was published April 2, 2026, with inventors Jinuk Kim and Hyun Oh Song. The invention relates to CPC classifications G06N 3/082 and G06N 3/0464, covering neural network optimization and compression techniques.
What changed
Samsung Electronics filed USPTO Patent Application US20260093989A1 for an electronic device configured to perform neural network lightweighting. The system generates candidate neural networks by excluding nonlinear layers from segmented networks (each segment containing nonlinear and convolution layers), selects optimal candidates based on importance and latency metrics for succession segments where convolution layers are successive, and produces final networks by merging successive convolution layers.
This patent application does not create compliance obligations for external parties. Technology companies developing AI/neural network products may wish to review the technical approach for freedom-to-operate considerations. The application publication date is April 2, 2026, with no external comment or compliance deadlines. Patent prosecution proceedings will continue between Samsung and USPTO.
Archived snapshot
Apr 2, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
ELECTRONIC DEVICE, TERMINAL, AND OPERATING METHOD WITH NEURAL NETWORK LIGHTWEIGHTING
Application US20260093989A1 Kind: A1 Apr 02, 2026
Assignee
SAMSUNG ELECTRONICS CO., LTD.
Inventors
Jinuk KIM, Hyun Oh SONG
Abstract
An electronic device includes one or more processors configured to generate a plurality of candidate neural networks in which one or more nonlinear layers are excluded from a neural network including a plurality of segments, each of the plurality of segments including a nonlinear layer and a convolution layer, select one candidate neural network from the plurality of candidate neural networks based on an importance value and a latency value for a succession segment included in each of the plurality of candidate neural networks where convolution layers are successive, and generate a final neural network in which the successive convolution layers are merged in the selected candidate neural network.
CPC Classifications
G06N 3/082 G06N 3/0464
Filing Date
2025-09-16
Application No.
19329970
Named provisions
Related changes
Get daily alerts for USPTO Patent Applications - AI & Computing (G06N)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The plain-English summary, classification, and "what to do next" steps are AI-generated from the original text. Cite the source document, not the AI analysis.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - AI & Computing (G06N) publishes new changes.