Analog Neural Networks as Decoders
暂无分享,去创建一个
Analog neural networks with feedback can be used to implement K- (Winner-Take-All (KWTA) networks. In turn, KWTA networks can be used as decoders of a class of nonlinear error-correcting codes. By interconnecting such KWTA networks, we can construct decoders capable of decoding more powerful codes. We consider several families of interconnected KWTA networks, analyze their performance in terms of coding theory metrics, and consider the feasibility of embedding such networks in VLSI technologies.
[1] Yaser S. Abu-Mostafa,et al. On the K-Winners-Take-All Network , 1988, NIPS.
[2] Ruth A. Erlanson. Soft-decision decoding of a family of nonlinear codes using a neural network , 1991 .
[3] John C. Platt,et al. Analog decoding using neural networks , 1987 .