Programmable integrated photonic coherent matrix: Principle, configuring, and applications

B Wu, H Zhou, J Dong, X Zhang - Applied Physics Reviews, 2024 - pubs.aip.org
Every multi-input multi-output linear optical system can be deemed as a matrix multiplier that
carries out a desired transformation on the input optical information, such as imaging …

Analog spatiotemporal feature extraction for cognitive radio-frequency sensing with integrated photonics

S Xu, B Liu, S Yi, J Wang, W Zou - Light: Science & Applications, 2024 - nature.com
Analog feature extraction (AFE) is an appealing strategy for low-latency and efficient
cognitive sensing systems since key features are much sparser than the Nyquist-sampled …

Correlated optical convolutional neural network with “quantum speedup”

Y Sun, Q Li, LJ Kong, X Zhang - Light: Science & Applications, 2024 - nature.com
Compared with electrical neural networks, optical neural networks (ONNs) have the
potentials to break the limit of the bandwidth and reduce the consumption of energy, and …

The Goldilocks principle of learning unitaries by interlacing fixed operators with programmable phase shifters on a photonic chip

K Zelaya, M Markowitz, MA Miri - Scientific Reports, 2024 - nature.com
Programmable photonic integrated circuits represent an emerging technology that
amalgamates photonics and electronics, paving the way for light-based information …

Signal-to-noise ratio enhancement for digitalizing low amplitude wideband signals in photonic analog-to-digital converters

R Qin, D Zhou, X Chen, L Zhang, J Wu, W Zou - Optics Express, 2024 - opg.optica.org
Photonic analog-to-digital converters (PADCs) have been investigated for nearly five
decades as a promising approach to overcome the bandwidth and jitter problem and bring …

Programmable Photonic Neural Networks for advanced Machine Learning tasks

A Totović, A Tsakyridis, G Giamougiannis… - Optical Fiber …, 2023 - opg.optica.org
Photonics holds the promise of resha** Machine Learning and High-Performance
Computing hardware landscape, strip** it of unnecessary signal conversion overhead …