摘要
详细介绍了一种基于递归神经网络(RNN)的1/n卷积码解码器的原理与实现。仿真结果表明RNN解码器与Vterbi解码器效果很接近,对一些特殊的卷积码,性能非常好。并通过模拟退火技术对此解码器的性能进行了改善。
In this paper a detailed principle and application of a 1/n rate convolution decoder based on Recurrent Neural Network(RNN) are introduced. Simulation results have confirmed that the RNN decoder is capable of performing very close to the Viterbi decoder and works very well for some specially structured convolution codes. In particular,decoding capabilities of RNN decoders are improved when Simulated Annealing(SA) technique has been used.
出处
《现代电子技术》
2007年第1期61-62,共2页
Modern Electronics Technique
基金
地理信息科学江苏省重点实验室开放基金资助(JK20050304)
关键词
卷积码
解码
噪声能量函数
退火算法
递归神经网络
convolution codes
decoding
noise energy function
simulated annealing
recurrent neural network