What Can Machine Learning Teach Us about Communications?

Rapid improvements in machine learning over the past decade are beginning to have far-reaching effects. For communications, engineers with limited domain expertise can now use off-the-shelf learning packages to design high-performance systems based on simulations. Prior to the current revolution in machine learning, the majority of communication engineers were quite aware that system parameters (such as filter coefficients) could be learned using stochastic gradient descent. It was not at all clear, however, that more complicated parts of the system architecture could be learned as well. In this paper, we discuss the application of machine-learning techniques to two communications problems and focus on what can be learned from the resulting systems. We were pleasantly surprised that the observed gains in one example have a simple explanation that only became clear in hindsight. In essence, deep learning discovered a simple and effective strategy that had not been considered earlier.

[1]  Henry D. Pfister,et al.  Wideband Time-Domain Digital Backpropagation via Subband Processing and Deep Learning , 2018, 2018 European Conference on Optical Communication (ECOC).

[2]  David Burshtein,et al.  Deep Learning Methods for Improved Decoding of Linear Codes , 2017, IEEE Journal of Selected Topics in Signal Processing.

[3]  Keith M. Chugg,et al.  Random Redundant Soft-In Soft-Out Decoding of Linear Block Codes , 2006, 2006 IEEE International Symposium on Information Theory.

[4]  Henry D. Pfister,et al.  Nonlinear Interference Mitigation via Deep Neural Networks , 2017, 2018 Optical Fiber Communications Conference and Exposition (OFC).

[5]  J. Kahn,et al.  Compensation of Dispersion and Nonlinear Impairments Using Digital Backpropagation , 2008, Journal of Lightwave Technology.

[6]  Arthur James Lowery,et al.  Improved single channel backpropagation for intra-channel fiber nonlinearity compensation in long-haul optical communication systems. , 2010, Optics express.

[7]  Stephan ten Brink,et al.  On deep learning-based channel decoding , 2017, 2017 51st Annual Conference on Information Sciences and Systems (CISS).

[8]  Yann LeCun,et al.  Learning Fast Approximations of Sparse Coding , 2010, ICML.

[9]  Jinghu Chen,et al.  Generating Code Representations Suitable for Belief Propagation Decoding , 2002 .

[10]  E. Mateo,et al.  Complementary FIR Filter Pair for Distributed Impairment Compensation of WDM Fiber Transmission , 2009, IEEE Photonics Technology Letters.

[11]  Johannes B. Huber,et al.  Multiple-bases belief-propagation decoding of high-density cyclic codes , 2009, IEEE Transactions on Communications.

[12]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[13]  Marc P. C. Fossorier,et al.  Iterative Decoding of Multiple-Step Majority Logic Decodable Codes , 2007, IEEE Transactions on Communications.

[14]  Govind P. Agrawal,et al.  Nonlinear Fiber Optics , 1989 .

[15]  William Shieh,et al.  End-to-End Energy Modeling and Analysis of Long-Haul Coherent Transmission Systems , 2014, Journal of Lightwave Technology.

[16]  L. G. Tallini,et al.  Neural nets for decoding error-correcting codes , 1995, IEEE Technical Applications Conference and Workshops. Northcon/95. Conference Record.

[17]  Per Larsson-Edefors,et al.  ASIC Implementation of Time-Domain Digital Backpropagation with Deep-Learned Chromatic Dispersion Filters , 2018, 2018 European Conference on Optical Communication (ECOC).

[18]  Henry D. Pfister,et al.  Deep Learning of the Nonlinear Schrödinger Equation in Fiber-Optic Communications , 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

[19]  Yoni Choukroun,et al.  Deep Learning for Decoding of Linear Codes - A Syndrome-Based Approach , 2018, 2018 IEEE International Symposium on Information Theory (ISIT).

[20]  Guifang Li,et al.  Efficient backward-propagation using wavelet-based filtering for fiber backward-propagation. , 2009, Optics express.

[21]  Mikael Mazur,et al.  Time-domain digital back propagation: Algorithm and finite-precision implementation aspects , 2017, 2017 Optical Fiber Communications Conference and Exhibition (OFC).

[22]  Yair Be'ery,et al.  Improved random redundant iterative HDPC decoding , 2009, IEEE Transactions on Communications.

[23]  Yair Be'ery,et al.  Learning to decode linear codes using deep learning , 2016, 2016 54th Annual Allerton Conference on Communication, Control, and Computing (Allerton).

[24]  Danish Rafique,et al.  Compensation of intra-channel nonlinear fibre impairments using simplified digital back-propagation algorithm. , 2011, Optics express.

[25]  Henry D. Pfister,et al.  Learned Belief-Propagation Decoding with Simple Scaling and SNR Adaptation , 2019, 2019 IEEE International Symposium on Information Theory (ISIT).