.png){kind=icon}
.png){kind=icon}
Return
STNet: Low-Complexity Neural Network Decoder With Network Pruning
.png){kind=icon}
PRE
AI
DOI：10.1109/LCOMM.2021.3128067.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this letter, a novel and compact neural network called Sigmoid-Tanh Network (STNet) is proposed for channel decoding, which is only composed of sigmoid and tanh activation functions. To address the structural redundancy problem in long and short-term memory network (LSTM), the neurons in the STNet are redesigned with the most effective structure in the LSTM cell for decoding. To further reduce the computational complexity, we propose an automatic pruning method based on multiple layer sensitivity, which can effectively remove redundant weights in STNet decoder with slight performance loss. Simulation results show that the proposed STNet decoder achieves near-maximum likelihood (ML) performance with only 17.1% trainable parameters compared to LSTM. Moreover, our pruning method achieves comparable decoding performance when reducing 58.3% Floating-point operations (FLOPs) for STNet.
Keywords:
Decoding
Sensitivity
Logic gates
Artificial neural networks
Neurons
Computer architecture
Microprocessors
Deep learning
channel decoding
LSTM
network pruning