Deep Learning for MIMO Channel Estimation: Interpretation, Performance, and Comparison

Deep learning (DL) has emerged as an effective tool for channel estimation in wireless communication systems, especially under some imperfect environments. However, even with such unprecedented success, DL methods are often regarded as black boxes and are lack of explanations on their internal mechanisms, which severely limits further improvement and extension. In this paper, we present a preliminary theoretical analysis on DL based channel estimation for multiple-antenna systems to understand and interpret its internal mechanism. Deep neural network (DNN) with rectified linear unit (ReLU) activation function is mathematically equivalent to a piecewise linear function. Hence, the corresponding DL estimator can achieve universal approximation to a large family of functions by making efficient use of piecewise linearity. We demonstrate that DL based channel estimation does not restrict to any specific signal model and approaches to the minimum mean-squared error (MMSE) estimation in various scenarios without requiring any prior knowledge of channel statistics. Therefore, DL based channel estimation outperforms or is at least comparable with traditional channel estimation, depending on the types of channels. Simulation results confirm the accuracy of the proposed interpretation and demonstrate the effectiveness of DL based channel estimation under both linear and nonlinear signal models.

[1]  Franco Scarselli,et al.  On the Complexity of Neural Network Classifiers: A Comparison Between Shallow and Deep Architectures , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[2]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[3]  Geoffrey Ye Li,et al.  Model-Driven Deep Learning for Physical Layer Communications , 2018, IEEE Wireless Communications.

[4]  Steven Kay,et al.  Fundamentals Of Statistical Signal Processing , 2001 .

[5]  Geoffrey Ye Li,et al.  ComNet: Combination of Deep Learning and Expert Knowledge in OFDM Receivers , 2018, IEEE Communications Letters.

[6]  Elena Costa,et al.  M-QAM-OFDM system performance in the presence of a nonlinear amplifier and phase noise , 2002, IEEE Trans. Commun..

[7]  Biing-Hwang Juang,et al.  Deep Learning in Physical Layer Communications , 2018, IEEE Wireless Communications.

[8]  Tao Jiang,et al.  Deep learning for wireless physical layer: Opportunities and challenges , 2017, China Communications.

[9]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[10]  Geoffrey Ye Li,et al.  Toward Intelligent Vehicular Networks: A Machine Learning Framework , 2018, IEEE Internet of Things Journal.

[11]  Yoshua Bengio,et al.  Shallow vs. Deep Sum-Product Networks , 2011, NIPS.

[12]  Matus Telgarsky,et al.  Benefits of Depth in Neural Networks , 2016, COLT.

[13]  Shi Jin,et al.  Deep Learning for Massive MIMO CSI Feedback , 2017, IEEE Wireless Communications Letters.

[14]  Geoffrey Ye Li,et al.  Deep Learning-Based CSI Feedback Approach for Time-Varying Massive MIMO Channels , 2018, IEEE Wireless Communications Letters.

[15]  Geoffrey Ye Li,et al.  Deep Learning-Based Channel Estimation for Beamspace mmWave Massive MIMO Systems , 2018, IEEE Wireless Communications Letters.

[16]  Biing-Hwang Juang,et al.  Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels , 2019, IEEE Transactions on Wireless Communications.

[17]  William Mendenhall,et al.  Introduction to Probability and Statistics , 1961, The Mathematical Gazette.

[18]  Jakob Hoydis,et al.  An Introduction to Deep Learning for the Physical Layer , 2017, IEEE Transactions on Cognitive Communications and Networking.

[19]  Geoffrey Ye Li,et al.  Power of Deep Learning for Channel Estimation and Signal Detection in OFDM Systems , 2017, IEEE Wireless Communications Letters.

[20]  Michail Matthaiou,et al.  Hardware-Constrained Millimeter-Wave Systems for 5G: Challenges, Opportunities, and Solutions , 2018, IEEE Communications Magazine.

[21]  Stephan ten Brink,et al.  Deep Learning Based Communication Over the Air , 2017, IEEE Journal of Selected Topics in Signal Processing.

[22]  Geoffrey Ye Li,et al.  Deep Learning-Based Downlink Channel Prediction for FDD Massive MIMO System , 2019, IEEE Communications Letters.

[23]  Hamid Sheikhzadeh,et al.  Deep Learning-Based Channel Estimation , 2018, IEEE Communications Letters.

[24]  Biing-Hwang Juang,et al.  Channel Agnostic End-to-End Learning Based Communication Systems with Conditional GAN , 2018, 2018 IEEE Globecom Workshops (GC Wkshps).

[25]  Xiaoli Ma,et al.  Deep Learning-Based Channel Estimation for Doubly Selective Fading Channels , 2019, IEEE Access.

[26]  Shi Jin,et al.  On the Uplink Achievable Rate of Massive MIMO System with Low-Resolution ADC and RF Impairments , 2019, IEEE Communications Letters.

[27]  Geoffrey Ye Li,et al.  Deep Reinforcement Learning Based Resource Allocation for V2V Communications , 2018, IEEE Transactions on Vehicular Technology.

[28]  Geoffrey Ye Li,et al.  Machine Learning for Vehicular Networks: Recent Advances and Application Examples , 2018, IEEE Vehicular Technology Magazine.

[29]  Erik G. Larsson,et al.  Scaling Up MIMO: Opportunities and Challenges with Very Large Arrays , 2012, IEEE Signal Process. Mag..

[30]  Razvan Pascanu,et al.  On the Number of Linear Regions of Deep Neural Networks , 2014, NIPS.

[31]  Raman Arora,et al.  Understanding Deep Neural Networks with Rectified Linear Units , 2016, Electron. Colloquium Comput. Complex..

[32]  George Cybenko,et al.  Approximation by superpositions of a sigmoidal function , 1989, Math. Control. Signals Syst..

[33]  Geoffrey Ye Li,et al.  Deep-Learning-Based Wireless Resource Allocation With Application to Vehicular Networks , 2019, Proceedings of the IEEE.

[34]  Elena Costa,et al.  Impact of amplifier nonlinearities on OFDM transmission system performance , 1999, IEEE Communications Letters.

[35]  Thia Kirubarajan,et al.  Estimation with Applications to Tracking and Navigation: Theory, Algorithms and Software , 2001 .

[36]  Jon A. Wellner,et al.  Weak Convergence and Empirical Processes: With Applications to Statistics , 1996 .

[37]  Guan Gui,et al.  Deep Learning for Super-Resolution Channel Estimation and DOA Estimation Based Massive MIMO System , 2018, IEEE Transactions on Vehicular Technology.