18362137. MACHINE-LEARNING ERROR-CORRECTING CODE CONTROLLER simplified abstract (SAMSUNG ELECTRONICS CO., LTD.)
MACHINE-LEARNING ERROR-CORRECTING CODE CONTROLLER
Organization Name
Inventor(s)
Ariel Doubchak of HERZLIYA (IL)
Dikla Shapiro of PETAH TIKVA (IL)
Evgeny Blaichman of TEL AVIV-YAFO (IL)
MACHINE-LEARNING ERROR-CORRECTING CODE CONTROLLER - A simplified explanation of the abstract
This abstract first appeared for US patent application 18362137 titled 'MACHINE-LEARNING ERROR-CORRECTING CODE CONTROLLER
Simplified Explanation
The abstract describes a machine-learning error-correcting code (ECC) controller that includes a hard-decision (HD) ECC decoder optimized for high-speed data throughput, a soft-decision (SD) ECC decoder optimized for high-correctability data throughput, and a machine-learning equalizer (MLE) that can select either the HD or SD ECC decoder based on data throughput requirements. The controller is designed to provide fast HD throughput using a linear ECC, specifically a soft Hamming permutation code (SHPC).
- The machine-learning ECC controller includes HD and SD ECC decoders and an MLE.
- The HD ECC decoder is optimized for high-speed data throughput.
- The SD ECC decoder is optimized for high-correctability data throughput.
- The MLE can dynamically select either the HD or SD ECC decoder based on data throughput requirements.
- The ML ECC controller utilizes a linear ECC, specifically a soft Hamming permutation code (SHPC).
Potential Applications
- High-speed data communication systems
- Error correction in storage devices
- Wireless communication systems
Problems Solved
- High-speed data transmission often requires sacrificing error correction capability.
- Traditional ECC controllers may not be able to adapt to varying data throughput requirements.
- The ML ECC controller solves these problems by providing both high-speed and high-correctability data throughput options.
Benefits
- Improved data throughput in high-speed communication systems.
- Enhanced error correction capability for reliable data transmission.
- Adaptive selection of ECC decoder based on data throughput requirements.
Original Abstract Submitted
A machine-learning (ML) error-correcting code (ECC) controller may include a hard-decision (HD) ECC decoder optimized for high-speed data throughput, a soft-decision (SD) ECC decoder optimized for high-correctability data throughput, and a machine-learning equalizer (MLE) configured to variably select one of the HD ECC decoder or the SD ECC decoder for data throughput. An embodiment of the ML ECC controller may provide speed-optimized HD throughput based on a linear ECC. The linear ECC may be a soft Hamming permutation code (SHPC).
