Neural Filter Design for Frequency Selective Channel Equalization

Abstract

Under frequency-selective multi-path channel environment, delayed copies of the transmitted symbols are summed up to form a received signal. In order to remove this intersymbol interference (ISI), linear minimum mean-square error (LMMSE) equalizer can be applied to the received signal to reconstruct the transmitted symbols. While being an optimal linear filter, the LMMSE equalizer ideally requires infinite length of the received signal, which is infeasible in practice. In order to mitigate this limitation of linear filters, we propose to utilize neural networks for equalization, referred to as neural filters. Numerical results verify that, given with enough pilot data, the proposed neural filter outperforms the optimal LMMSE equalizer that uses perfect knowledge on the channel realization vector.