Neural networks (NNs) inspired by the forward-backward algorithm (FBA) are used as equalizers for bandlimited channels with a memoryless nonlinearity. The NN-equalizers are combined with successive interference cancellation (SIC) to approach the information rates of joint detection and decoding (JDD) with considerably less complexity than JDD and other existing equalizers. Simulations for short-haul optical fiber links with square-law detection illustrate the gains of NNs as compared to the complexity-limited FBA and Gibbs sampling.

翻译：受前向-后向算法（FBA）启发的神经网络（NN）被用作带记忆非线性特性的带限信道的均衡器。这些神经网络均衡器与串行干扰消除（SIC）相结合，能够以远低于联合检测与解码（JDD）及其他现有均衡器的复杂度，逼近JDD的信息传输速率。针对采用平方律检测的短距光纤链路的仿真结果表明，与复杂度受限的FBA和吉布斯采样相比，神经网络具有显著性能优势。