Spatial multiplexing in optical neural networks is repurposed as a trainable representational coordinate, demonstrated in multi-layer architectures for image classification, regression, and hybrid vision-language captioning with over one million optical phase parameters.
Analysis of diffractive optical neural networks and their integration with electronic neural networks.IEEE Journal of Selected Topics in Quantum Electronics, 26(1):8732486, 2020
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
physics.optics 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
A free-space PELM achieves 96.56% on MNIST, 95.67% on spoken digit spectrograms, 100% on mushroom classification, and 0.0699 NRMSE on abalone regression using the same optical setup, claimed as the first multimodal free-space PELM.
citing papers explorer
-
Multi-channel Optical Vision Model
Spatial multiplexing in optical neural networks is repurposed as a trainable representational coordinate, demonstrated in multi-layer architectures for image classification, regression, and hybrid vision-language captioning with over one million optical phase parameters.
-
Multimodal Optical Feature Extraction with a Free-Space Photonic Extreme Learning Machine
A free-space PELM achieves 96.56% on MNIST, 95.67% on spoken digit spectrograms, 100% on mushroom classification, and 0.0699 NRMSE on abalone regression using the same optical setup, claimed as the first multimodal free-space PELM.