Joint optimization of input and readout layers halves photonic reservoir node count while improving BER by >100x and memory performance by >1000x in optical equalization up to 200 km.
Highly parallel simulation and op- timization of photonic circuits in time and frequency domain based on the deep-learning framework pytorch
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.optics 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Node-reduction through Joint Optimization of Input and Readout Layers in Photonic Reservoir Equalization
Joint optimization of input and readout layers halves photonic reservoir node count while improving BER by >100x and memory performance by >1000x in optical equalization up to 200 km.