Neural Network Device with Non-Linear Operations

ChangeBridge: Patent Apps - AI & Computing (G06N)

Published June 26th, 2025

Detected April 3rd, 2026

Summary

Samsung Electronics Co., Ltd. filed US Patent Application US20260094027A1 with the USPTO for an electronic device executing neural network models with non-linear operations. The invention covers updating weights between neural network nodes based on reference node values, with inventors including Chang-Woo Shin, Carlos Cristiano De Jesus Alcantara, Anes Ju, and Kitae Park. The application was published on April 2, 2026.

View original document View source feed page

What changed

Samsung Electronics Co., Ltd. filed US Patent Application US20260094027A1 covering neural network weight update mechanisms in an electronic device. The invention describes an inference process where weights applied when transmitting values between nodes in a neural network are updated based on values of a reference node. The patent covers both the electronic device and its operation method for executing neural network models including non-linear operations.

Companies developing neural network hardware or software should monitor this patent for potential licensing implications or freedom-to-operate concerns. No immediate compliance actions are required from this publication alone, but organizations in AI/neural network technology sectors should review this application for competitive intelligence and potential blocking patents.

Source document (simplified)

← USPTO Patent Applications

ELECTRONIC DEVICE FOR EXECUTING NEURAL NETWORK MODEL INCLUDING NONLINEAR OPERATION AND OPERATION METHOD THEREOF

Application US20260094027A1 Kind: A1 Apr 02, 2026

Assignee

SAMSUNG ELECTRONICS CO., LTD.

Inventors

Chang-Woo SHIN, Carlos Cristiano De Jesus Alcantara, Anes Ju, Kitae Park

Abstract

An electronic device for executing a neural network model including a non-linear operation and an operation method thereof are provided. The operation method of the electronic device includes obtaining data to be inferred and obtaining an inference result of the data output from the neural network model as the data is input to the neural network model including a plurality of nodes, wherein, in an inference process, a first weight applied when a value of a first node among the plurality of nodes is transmitted to a second node may be updated based on a value of a first reference node, which is any one of the plurality of nodes.