Deep neural network implementation for concatenated codes
US12176924B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 16, 2023 |
| Grant date | Dec 24, 2024 |
| Priority date | — |
| Expiry date | Jun 14, 2043 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH03M13/09
- WIPO fieldBasic communication processes
- WIPO sectorElectrical engineering
Abstract
Systems, methods, non-transitory computer-readable media configured to perform operations associated with a storage medium. One system includes the storage medium and an encoding/decoding (ED) system, the ED system being configured to receive a set of input log-likelihood ratios (LLRs) of a component of the plurality of components, determine an extrinsic estimation function based on a set of features of the set of input LLRs, analyze the extrinsic estimation function to obtain a plurality of extrinsic LLR values, map the plurality of extrinsic LLR values to an input LLR of the set of input LLRs, and output, for each component, a plurality of updated LLR values based on the mapping.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.