Configurable neural network for channel state feedback (CSF) learning

US11984955B2 · kind B2 · utility

Assignee

• QUALCOMM Incorporated · US

Inventors

• Bo Chen · Beijing, CN
• Pavan Kumar Vitthaladevuni · San Diego, US
• Taesang Yoo · Riverside, US
• Naga Bhushan · San Diego, US
• Jay Kumar Sundararajan · San Diego, US
• Ruifeng MA · Beijing, CN
• June Namgoong · San Diego, US
• Krishna Kiran Mukkavilli · San Diego, US
• Hao Xu · Cupertino, US
• Tingfang Ji · San Diego, US

Key dates

• Filing date: Apr 17, 2020
• Grant date: May 14, 2024
• Expiry date: Apr 17, 2040

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/098
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

A method of wireless communication, by a user equipment (UE), includes receiving multiple neural network training configurations for channel state feedback (CSF). Each configuration corresponds to a different neural network framework. The method also includes training each of a group of neural network decoder/encoder pairs in accordance with the received training configurations. A method of wireless communication, by a base station, includes transmitting multiple neural network training configurations to a user equipment (UE) for channel state feedback (CSF). Each configuration corresponds to a different neural network framework. The method also includes receiving a neural network decoder/encoder pair trained in accordance with the training configurations.