Scalable Optical Learning Operator
December 22, 2020 Β· Declared Dead Β· π Nature Computational Science
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
UΔur TeΔin, Mustafa YΔ±ldΔ±rΔ±m, Δ°lker OΔuz, Christophe Moser, Demetri Psaltis
arXiv ID
2012.12404
Category
physics.optics
Cross-listed
cs.LG,
eess.IV
Citations
147
Venue
Nature Computational Science
Last Checked
1 month ago
Abstract
Today's heavy machine learning tasks are fueled by large datasets. Computing is performed with power hungry processors whose performance is ultimately limited by the data transfer to and from memory. Optics is one of the powerful means of communicating and processing information and there is intense current interest in optical information processing for realizing high-speed computations. Here we present and experimentally demonstrate an optical computing framework based on spatiotemporal effects in multimode fibers for a range of learning tasks from classifying COVID-19 X-ray lung images and speech recognition to predicting age from face images. The presented framework overcomes the energy scaling problem of existing systems without compromising speed. We leveraged simultaneous, linear, and nonlinear interaction of spatial modes as a computation engine. We numerically and experimentally showed the ability of the method to execute several different tasks with accuracy comparable to a digital implementation.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β physics.optics
R.I.P.
π»
Ghosted
R.I.P.
π»
Ghosted
Training of photonic neural networks through in situ backpropagation
R.I.P.
π»
Ghosted
Experimental robustness of Fourier Ptychography phase retrieval algorithms
R.I.P.
π»
Ghosted
The physics of optical computing
R.I.P.
π»
Ghosted
Freeform Diffractive Metagrating Design Based on Generative Adversarial Networks
R.I.P.
π»
Ghosted
Deep Learning Reconstruction of Ultra-Short Pulses
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Language Models are Few-Shot Learners
R.I.P.
π»
Ghosted
PyTorch: An Imperative Style, High-Performance Deep Learning Library
R.I.P.
π»
Ghosted
XGBoost: A Scalable Tree Boosting System
R.I.P.
π»
Ghosted