EPO Patent: Machine Learning for Wireless Communication Non-linearity
Summary
The European Patent Office has published a patent application by QUALCOMM Incorporated detailing the use of machine learning, specifically neural networks, to address non-linearity in wireless communication transmit power amplifiers. The patent describes methods for encoding and decoding transmit waveforms to compensate for distortion errors.
What changed
This document is a patent bulletin from the European Patent Office (EPO) announcing a new patent application (EP4657757A3) by QUALCOMM Incorporated. The patent focuses on the application of machine learning, particularly auto-encoder neural networks, to mitigate non-linearity issues in power amplifiers (PAs) during wireless transmissions. It outlines methods for a transmitting device to transform a transmit waveform using an encoder neural network to control PA operation and for a receiving device to recover original symbols using a decoder neural network.
This is a patent application, not a regulatory rule or guidance. Therefore, it does not impose direct compliance obligations on regulated entities. However, it signals technological advancements in wireless communication that may influence future industry standards or intellectual property landscapes. Companies involved in wireless communication technology, particularly those manufacturing or developing power amplifiers and communication systems, should be aware of such patented innovations for competitive and strategic planning purposes.
Source document (simplified)
MACHINE LEARNING FOR ADDRESSING TRANSMIT (TX) NON-LINEARITY
Search Report EP4657757A3 Kind: A3 Mar 18, 2026
Applicants
QUALCOMM Incorporated
Inventors
NAMGOONG, June, YOO, Taesang, BHUSHAN, Naga, MUKKAVILLI, Krishna Kiran, JI, Tingfang
Abstract
A method of wireless communication by a transmitting device transforms a transmit waveform by an encoder neural network to control power amplifier (PA) operation with respect to non-linearities. The method also transmits the transformed transmit waveform across a propagation channel. A method of wireless communication by a receiving device receives a waveform transformed by an encoder neural network. The method also recovers, with a decoder neural network, the encoder input symbols from the received waveform. A transmitting device for wireless communication calculates distortion error based on a non-distorted digital transmit waveform and a distorted digital transmit waveform. The transmitting device also compresses the distortion error with an encoder neural network of an auto-encoder. The transmitting device transmits to a receiving device the compressed distortion error to compensate for power amplifier (PA) non-linearity.
IPC Classifications
H04L 27/26 20060101AFI20260210BHEP G06N 3/02 20060101ALI20260210BHEP G06N 20/00 20190101ALI20260210BHEP H03M 7/30 20060101ALI20260210BHEP H04L 27/36 20060101ALI20260210BHEP
Designated States
AL, AT, BE, BG, CH, CY, CZ, DE, DK, EE, ES, FI, FR, GB, GR, HR, HU, IE, IS, IT, LI, LT, LU, LV, MC, MK, MT, NL, NO, PL, PT, RO, RS, SE, SI, SK, SM, TR
Named provisions
Related changes
Source
Classification
Who this affects
Taxonomy
Browse Categories
Get Telecom & Technology alerts
Weekly digest. AI-summarized, no noise.
Free. Unsubscribe anytime.
Get alerts for this source
We'll email you when ChangeBridge: EPO Bulletin - AI & Computing (G06N) publishes new changes.