With the rapid development of optical communication systems, more advanced techniques
conventionally used in long-haul transmissions have gradually entered systems covering …

Optical transmission links are generally composed of optical fibers, optical amplifiers, and
optical filters. In this paper, we present a channel reconstruction method (CRM) that extracts …

In this paper, a novel deep learning architecture, Fourier neural operator (FNO), has been
introduced to ap-proximate the nonlinear Schrodinger equation which characterizes fiber …

Bidirectional recurrent neural networks (bi-RNNs), in particular bidirectional long short term
memory (bi-LSTM), bidirectional gated recurrent unit, and convolutional bi-LSTM models …

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 that of …

We design and implement an adaptive machine learning equalizer that alternates multiple
linear and nonlinear computational layers on an FPGA. On-chip training via gradient …

In this paper, we investigate the use of the learned digital back-propagation (LDBP) for
equalizing dual-polarization fiber-optic transmission in dispersion-managed (DM) links …

Nonlinear signal distortions are one of the primary factors limiting the capacity and reach of
optical transmission systems. Currently, several approaches exist for compensating …

Overcoming fiber nonlinearity is one of the core challenges limiting the capacity of optical
fiber communication systems. Machine learning based solutions such as learned digital …

Taking optical frequency combs as WDM laser sources for coherent optical communication
systems has great potential in low-cost, low-complexity, and large-capacity communications …