Channel Equalization Through Reservoir Computing: A Theoretical Perspective
- 6 January 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Wireless Communications Letters
- Vol. 12 (5) , 774-778
Abstract
Deep learning practice, including in wireless communications, often relies on trial and error to optimize neural network (NN) structures and their corresponding hyperparameters. We show that Reservoir Computing, especially the Echo State Network (ESN), is an ideal learning-based equalizer for a general fading channel and for an ESN equalizing a channel with known statistics, theoretically derive its optimum reservoir weights which are randomly initialized in state-of-the-art and lack interpretability. The theoretical results are validated with simulations. In contrast to existing literature, this work analytically adapts the NN structure to the problem being addressed, guaranteeing optimum equalization under known channel statistics.Keywords
Funding Information
- U.S. National Science Foundation (CNS-2003059, CNS-2002908)
This publication has 12 references indexed in Scilit:
- Optimizing memory in reservoir computersChaos: An Interdisciplinary Journal of Nonlinear Science, 2022
- Echo State Networks trained by Tikhonov least squares are approximators of ergodic dynamical systemsPhysica D: Nonlinear Phenomena, 2021
- RCNet: Incorporating Structural Information Into Deep RNN for Online MIMO-OFDM Symbol Detection With Limited TrainingIEEE Transactions on Wireless Communications, 2021
- On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMDChaos: An Interdisciplinary Journal of Nonlinear Science, 2021
- Deep Echo State Q-Network (DEQN) and Its Application in Dynamic Spectrum Sharing for 5G and BeyondIEEE Transactions on Neural Networks and Learning Systems, 2020
- Adaptive Neural Signal Detection for Massive MIMOIEEE Transactions on Wireless Communications, 2020
- Learning for Detection: MIMO-OFDM Symbol Detection Through Downlink PilotsIEEE Transactions on Wireless Communications, 2020
- Machine learning based on reservoir computing with time-delayed optoelectronic and photonic systemsChaos: An Interdisciplinary Journal of Nonlinear Science, 2020
- Good and bad predictions: Assessing and improving the replication of chaotic attractors by means of reservoir computingChaos: An Interdisciplinary Journal of Nonlinear Science, 2019
- Learning to DetectIEEE Transactions on Signal Processing, 2019