TR2019-088

Neural Turbo Equalization to Mitigate Fiber Nonlinearity


We propose a turbo equalization scheme based on deep neural networks (DNN) to compensate for fiber nonlinearity. The turbo DNN equalizer can accelerate decoding convergence and achieve a significant gain of about 2 dB in nonlinear regimes.

 

  • Related News & Events

    •  NEWS   MERL Scientists Presenting 5 Papers including 2 Invited Talks at European Conference on Optical Communication (ECOC) 2019
      Date: September 22, 2019 - September 26, 2019
      MERL Contacts: Devesh Jha; Toshiaki Koike-Akino; Keisuke Kojima; David Millar; Kieran Parsons; Ye Wang
      Research Areas: Artificial Intelligence, Communications, Electronic and Photonic Devices, Optimization, Signal Processing
      Brief
      • MERL Optical Team scientists will be presenting 5 papers including 2 invited talks at the 45th European Conference on Optical Communication (ECOC) 2019, which is being held in Dublin from September 22-26, 2019. Topics to be presented include recent advances in sophisticated constellation shaping schemes, lattice coding, and deep learning-based turbo equalization to mitigate fiber nonlinearity. Dr. Kojima is giving an invited workshop talk on deep learning-based nano-photonic device optimization. Dr. Tobias Fehenberger, a former Visiting Scientist is giving an invited talk related to our joint paper "Mapping Strategies for Short-Length Probabilistic Shaping"

        ECOC is the largest optical communications event in Europe and a key meeting place for more than 1,500 scientists and researchers from institutions and companies across the world. The conference features more than 400 oral and poster presentations from various major telecoms industries and universities. As well as being one of the largest scientific conferences globally, ECOC also features Europe’s largest optical communications exhibition.
    •