A trained multi-layer TiO2 metasurface is shown in simulation to classify MNIST digits by focusing light to positions that encode the digit class, with up to 90% test accuracy.
MNIST handwritten digit database, Yann LeCun, Corinna Cortes and Chris Burges
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
physics.app-ph 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Neuromorphic Metasurface
A trained multi-layer TiO2 metasurface is shown in simulation to classify MNIST digits by focusing light to positions that encode the digit class, with up to 90% test accuracy.