Blind Channel Equalization Using Variational Autoencoders

Abstract

A new maximum likelihood estimation approach for blind channel equalization, using variational autoencoders (VAEs), is introduced. Significant and consistent improvements in the error rate of the reconstructed symbols, compared to constant modulus equalizers, are demonstrated. In fact, for the channels that were examined, the performance of the new VAE blind channel equalizer was close to the performance of a nonblind adaptive linear minimum mean square error equalizer. The new equalization method enables a significantly lower latency channel acquisition compared to the constant modulus algorithm (CMA). The VAE uses a convolutional neural network with two layers and a very small number of free parameters. Although the computational complexity of the new equalizer is higher compared to CMA, it is still reasonable, and the number of free parameters to estimate is small.

ViterbiNet: A Deep Learning Based Viterbi Algorithm for Symbol Detection

“…Decoding of structured codes using DNNs was considered in [12], while symbol recovery in multiple-input multiple-output (MIMO) systems was treated in [13]. The work [14] used variational autoencoders for equalizing linear multipath channels. Sequence detection using bi-directional recurrent neural networks (RNNs) was proposed in [15], while [16] considered a new ML-based channel decoder by combining convolutional neural networks with belief propagation.…”

A Learning Approach to Wireless Information and Power Transfer Signal and System Design

“…In particular, the similarities between the autoencoder architecture and the digital communication systems have motivated significant research efforts in the direction of modelling end-to-end communication systems using the autoencoder architecture [10,11]. Some examples of such designs include decoder design for existing channel codes [12], blind channel equalization [13], learning physical layer signal representation for SISO [14] and MIMO systems [15], OFDM systems [16,17].…”

A Joint Demodulation and Estimation Algorithm for Plasma Sheath Channel: Extract Principal Curves With Deep Learning

“…Recently, some researches have applied DL in channel estimation [2] [3]. T. J. O'Shea, who has made many contributions to combine DL and communication signal processing, points out that the potential of DL in the physical layer mainly comes from the following two aspects [4]: First, most communication signal processing methods are under the assumption of the existing theoretical channel model (e.g., liner, stationary or Gaussian and so on).…”