Long Short-Term Memory Neuron Equalizer.

In this work we propose a neuromorphic hardware based signal equalizer by based on the deep learning implementation. The proposed neural equalizer is plasticity trainable equalizer which is different from traditional model designed based DFE. A trainable Long Short-Term memory neural network based DFE architecture is proposed for signal recovering and digital implementation is evaluated through FPGA implementation. Constructing with modelling based equalization methods, the proposed approach is compatible to multiple frequency signal equalization instead of single type signal equalization. We shows quantitatively that the neuronmorphic equalizer which is amenable both analog and digital implementation outperforms in different metrics in comparison with benchmarks approaches. The proposed method is adaptable both for general neuromorphic computing or ASIC instruments.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Harald Haas,et al.  Neural Network-Based Joint Spatial and Temporal Equalization for MIMO-VLC System , 2019, IEEE Photonics Technology Letters.

[3]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[4]  Benjamin R. Taub.  SVM based method for multi-equalizer optimization , 2019, 2019 IEEE International Conference on Microwaves, Antennas, Communications and Electronic Systems (COMCAS).

[5]  Zurab Kiguradze,et al.  Bayesian Optimization for High-Speed Channel Equalization , 2019, 2019 Electrical Design of Advanced Packaging and Systems (EDAPS).

[6]  Yann LeCun,et al.  1.1 Deep Learning Hardware: Past, Present, and Future , 2019, 2019 IEEE International Solid- State Circuits Conference - (ISSCC).

[7]  Elif Derya Übeyli.  Combining recurrent neural networks with eigenvector methods for classification of ECG beats , 2009, Digit. Signal Process..

[8]  Narayan Srinivasa,et al.  Low-Power Neuromorphic Hardware for Signal Processing Applications: A review of architectural and system-level design approaches , 2019, IEEE Signal Processing Magazine.

[9]  Mingyu Wang,et al.  ERA-LSTM: An Efficient ReRAM-Based Architecture for Long Short-Term Memory , 2020, IEEE Transactions on Parallel and Distributed Systems.

[10]  Fan Zhang,et al.  AdaNN: Adaptive Neural Network-Based Equalizer via Online Semi-Supervised Learning , 2019, Journal of Lightwave Technology.

[11]  Qing Chen,et al.  Long Short-Term Memory Network Design for Analog Computing , 2019, ACM J. Emerg. Technol. Comput. Syst..

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

[13]  Weisheng Hu,et al.  A Powerful Equalizer Based on Modified SVM Classifier Without Nonlinear Kernel Enabled 100-Gb/s NG-EPON System With 10-G Class , 2019, IEEE Access.

[14]  Geoffrey E. Hinton,et al.  Learning representations by back-propagating errors , 1986, Nature.

[15]  R.G. Harley,et al.  A comparison of MLP, RNN and ESN in determining harmonic contributions from nonlinear loads , 2008, 2008 34th Annual Conference of IEEE Industrial Electronics.

[16]  Marie-Laure Boucheret,et al.  Neural networks-based turbo equalization of a satellite communication channel , 2014, 2014 IEEE 15th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC).

[17]  Jian Chen,et al.  137 Gb/s PAM-4 Transmissions at 850 nm over 40 cm Optical Backplane with 25 G Devices with Improved Neural Network-Based Equalization , 2019, Applied Sciences.

[18]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[19]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[20]  Sheng Chen,et al.  Adaptive Bayesian equalizer with decision feedback , 1993, IEEE Trans. Signal Process..

[21]  Nikil D. Dutt,et al.  Mapping Spiking Neural Networks to Neuromorphic Hardware , 2019, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[22]  Amin Karbasi,et al.  Submodularity in Action: From Machine Learning to Signal Processing Applications , 2020, IEEE Signal Processing Magazine.

[23]  Shiunn-Jang Chern,et al.  Semi-blind channel estimation scheme with Bayesian DFE for PRP-OFDM system , 2015, 2015 International Symposium on Intelligent Signal Processing and Communication Systems (ISPACS).

[24]  Alexander Kolesnikov,et al.  S4L: Self-Supervised Semi-Supervised Learning , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[25]  Xuqiang Zheng,et al.  A 50–112-Gb/s PAM-4 Transmitter With a Fractional-Spaced FFE in 65-nm CMOS , 2020, IEEE Journal of Solid-State Circuits.

[26]  Jri Lee,et al.  A 21-Gb/s 87-mW Transceiver With FFE/DFE/Analog Equalizer in 65-nm CMOS Technology , 2010, IEEE Journal of Solid-State Circuits.

[27]  George Kurian,et al.  Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation , 2016, ArXiv.

[28]  Geoffrey Zweig,et al.  LSTM time and frequency recurrence for automatic speech recognition , 2015, 2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU).

[29]  Takashi Morie,et al.  A Hardware-Oriented Dropout Algorithm for Efficient FPGA Implementation , 2017, ICONIP.

[30]  Candice Müller,et al.  Blind Fuzzy Adaptation Step Control for a Concurrent Neural Network Equalizer , 2019, Wirel. Commun. Mob. Comput..

[31]  Yingli Tian,et al.  Self-Supervised Visual Feature Learning With Deep Neural Networks: A Survey , 2019, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Hong-June Park,et al.  An 18-Gb/s NRZ Transceiver With a Channel-Included 2-UI Impulse-Response Filtering FFE and 1-Tap DFE Compensating up to 32-dB Loss , 2020, IEEE Transactions on Circuits and Systems II: Express Briefs.

[33]  Fan Chen,et al.  Equalization with Neural Network Circuitry for High-Speed Signal Link , 2019, 2019 IEEE International Symposium on Electromagnetic Compatibility, Signal & Power Integrity (EMC+SIPI).

[34]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.