Randomizing deep neural networks for telecommunications
Patent Information
- Application Number
- EP2024740718
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-06-16
- Filing Date
- 2024-06-14
- Publication Date
- 2026-01-21
AI Technical Summary
Conventional deep neural networks (DNNs) in telecommunications struggle to dynamically control transmission signals to maintain a white noise interference level, leading to potential transmission spikes and interference, especially when processing varying input data combinations.
A method involving a scrambling DNN operation that selects neural network scrambling information (NNSI) to reconfigure the transmitting DNN, ensuring the output communication signal meets the desired white noise interference level, with corresponding control messages directing the receiving DNN for effective descrambling and interference reduction.
This approach efficiently maintains a white noise interference level, prevents transmission spikes, and synchronizes transmitting and receiving DNNs to ensure reliable communication while maintaining signal quality and reducing interference.
Smart Images

Figure US2024034057_19122024_PF_FP_ABST