3 papers
physics.optics2026
Node-reduction through Joint Optimization of Input and Readout Layers in Photonic Reservoir Equalization
Ruben Van Assche, Sarah Masaad, Peter Bienstman
Photonic reservoir computing is a machine learning paradigm in which a recurrent neural network remains fixed while only the output weights are trained. This makes it a well-suited…
physics.optics2026
Baudrate- and Reach-Flexible All-Optical Equalization with a Co-Packaged Photonic Reservoir and Receiver
Sarah Masaad, Jakob Declercq, Stijn Sackesyn +10
Intensity-modulation direct-detection links must support increasing baudrates and transmission distances while operating under stringent power and cost constraints. However, as dat…
physics.optics2025
Real-time all-optical signal equalisation with silicon photonic recurrent neural networks
Ruben Van Assche, Sarah Masaad, Emmanuel Gooskens +4
Communication through optical fibres experiences limitations due to chromatic dispersion and nonlinear Kerr effects that degrade the signal. Mitigating these impairments is typical…