Former TRANSNET student wins UCL thesis prize
TRANSNET friend and former student researcher, Dr Boris Karanov, has been awarded the 2021 Fabrizio Lombardi Prize for his PhD thesis.
The Lombardi prize is awarded annually by UCL’s Department of Electronic and Electrical Engineering, given to the student who submitted the best PhD thesis over the previous year.
The 2021 Fabrizio Lombardi Prize was awarded to Boris Karanov for his PhD thesis ‘End-to-End Deep Learning in Optical Fibre Communication Systems’ which he submitted and successfully defended in 2020. Read the abstract below.
Boris completed his PhD programme with the Optical Networks Group at UCL between 2016 and 2020 as part of the COIN project (Coding for Optical communications In the Nonlinear regime) funded by the European Union's Horizon 2020 research and innovation program under the Marie-Skłodowska-Curie grant agreement No.676448.
His research focused on developing new coding and detection methods for communication over the nonlinear dispersive optical fibre channel using deep learning, under the supervision of TRANSNET director Professor Polina Bayvel. Boris is now a postdoctoral researcher with the Signal Processing Systems Group at the Technical University of Eindhoven.
The Lombardi Prize money has been generously donated by Professor Fabrizio Lombardi, a distinguished alumnus of the department who received both his MSc and PhD from UCL in the field of Microwave Engineering.
Abstract
Conventional communication systems consist of several signal processing blocks, each performing an individual task at the transmitter or receiver, e.g. coding, modulation, or equalisation. However, there is a lack of optimal, computationally feasible algorithms for nonlinear fibre communications as most techniques are based upon classical communication theory, assuming a linear or perturbed by a small nonlinearity channel. Consequently, the optimal end-to-end system performance cannot be achieved using transceivers with sub-optimum modules. Carefully chosen approximations are required to exploit the data transmission potential of optical fibres.
In this thesis, novel transceiver designs tailored to the nonlinear dispersive fibre channel using the universal function approximator properties of artificial neural networks (ANNs) are proposed and experimentally verified. The fibre-optic system is implemented as an end-to-end ANN to allow transceiver optimisation over all channel constraints in a single deep learning process. While the work concentrates on highly nonlinear short-reach intensity modulation/direct detection (IM/DD) fibre links, the developed concepts are general and applicable to different models and systems.
Found in many data centre, metro and access networks, the IM/DD links are severely impaired by the dispersion-induced inter-symbol interference and square law photodetection, rendering the communication channel nonlinear with memory. First, a transceiver based on a simple feedforward ANN (FFNN) is investigated and a training method for robustness to link variations is proposed. An improved recurrent ANN-based design is developed next, addressing the FFNN limitations in handling the channel memory. The systems’ performance is verified in first-in-field experiments, showing a substantial increase in transmission distances and data rates compared to classical signal processing schemes. A novel algorithm for end-to-end optimisation using experimentally collected data and generative adversarial networks is also developed, tailoring the transceiver to the specific properties of the transmission link. The research is a key milestone towards end-to-end optimised data transmission over nonlinear fibre systems.
Download the complete thesis by clicking on the link below.
End-to-End Deep Learning in Optical Fibre Communication Systems
Best thesis, best paper
As well as receiving the 2021 Lombardi Prize for his PhD thesis, Boris also won the Journal of Lightwave Technology Best Paper Award early this year for the publication ‘End-to-End Deep Learning of Optical Fiber Communications'. The award recognises some of the most influential and top-cited original papers published in the journal.
Congratulations from all the team, Boris!