4 papers
LDPC Decoding with Degree-Specific Neural Message Weights and RCQ Decoding
Linfang Wang, Caleb Terrill, Richard Wesel +1
Recently, neural networks have improved MinSum message-passing decoders for low-density parity-check (LDPC) codes by multiplying or adding weights to the messages, where the weight…
Reconstruction-Computation-Quantization (RCQ): A Paradigm for Low Bit Width LDPC Decoding
Linfang Wang, Caleb Terrill, Maximilian Stark +7
This paper uses the reconstruction-computation-quantization (RCQ) paradigm to decode low-density parity-check (LDPC) codes. RCQ facilitates dynamic non-uniform quantization to achi…
BEANNA: A Binary-Enabled Architecture for Neural Network Acceleration
Caleb Terrill, Fred Chu
Modern hardware design trends have shifted towards specialized hardware acceleration for computationally intensive tasks like machine learning and computer vision. While these comp…
FPGA Implementations of Layered MinSum LDPC Decoders Using RCQ Message Passing
Caleb Terrill, Linfang Wang, Sean Chen +4
Non-uniform message quantization techniques such as reconstruction-computation-quantization (RCQ) improve error-correction performance and decrease hardware complexity of low-densi…