82 citations · 239 across the 26 of their papers we have counts for
6 papers · 1 filter
Knowledge Distillation Applied to Optical Channel Equalization: Solving the Parallelization Problem of Recurrent Connection
Sasipim Srivallapanondh, Pedro J. Freire, Bernhard Spinnler +4
To circumvent the non-parallelizability of recurrent neural network-based equalizers, we propose knowledge distillation to recast the RNN into a parallelizable feedforward structur…
Implementing Neural Network-Based Equalizers in a Coherent Optical Transmission System Using Field-Programmable Gate Arrays
Pedro J. Freire, Sasipim Srivallapanondh, Michael Anderson +9
In this work, we demonstrate the offline FPGA realization of both recurrent and feedforward neural network (NN)-based equalizers for nonlinearity compensation in coherent optical t…
Reducing Computational Complexity of Neural Networks in Optical Channel Equalization: From Concepts to Implementation
Pedro J. Freire, Antonio Napoli, Diego Arguello Ron +7
In this paper, a new methodology is proposed that allows for the low-complexity development of neural network (NN) based equalizers for the mitigation of impairments in high-speed…
Towards FPGA Implementation of Neural Network-Based Nonlinearity Mitigation Equalizers in Coherent Optical Transmission Systems
Pedro J. Freire, Michael Anderson, Bernhard Spinnler +8
For the first time, recurrent and feedforward neural network-based equalizers for nonlinearity compensation are implemented in an FPGA, with a level of complexity comparable to tha…
Computational Complexity Evaluation of Neural Network Applications in Signal Processing
Pedro Freire, Sasipim Srivallapanondh, Antonio Napoli +2
In this paper, we provide a systematic approach for assessing and comparing the computational complexity of neural network layers in digital signal processing. We provide and link…
Domain Adaptation: the Key Enabler of Neural Network Equalizers in Coherent Optical Systems
Pedro J. Freire, Bernhard Spinnler, Daniel Abode +7
We introduce the domain adaptation and randomization approach for calibrating neural network-based equalizers for real transmissions, using synthetic data. The approach renders up…