Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Pushing the limits of optical information storage using deep learning

Abstract : Diffraction drastically limits the bit density in optical data storage. To increase the storage density, alternative strategies involving supplementary recording dimensions and robust read-out schemes must be explored. Here, we propose to encode multiple bits of information in the geometry of subwavelength dielectric nanostructures. A crucial problem in high-density information storage concepts is the robustness of the information readout with respect to fabrication errors and experimental noise. Using a machine-learning based approach in which the scattering spectra are analyzed by an artificial neural network, we achieve quasi error free read-out of 4-bit sequences, encoded in top-down fabricated silicon nanostructures. The read-out speed can further be increased exploiting the RGB values of microscopy images, and the information density could be increased beyond current state of the art. Our work paves the way towards high-density optical information storage using planar silicon nanostructures, compatible with mass-production ready CMOS technology.
Complete list of metadatas
Contributor : Peter Wiecha <>
Submitted on : Friday, July 27, 2018 - 10:28:36 AM
Last modification on : Wednesday, October 21, 2020 - 10:08:03 AM

Links full text


  • HAL Id : hal-01850258, version 1
  • ARXIV : 1805.03468


Peter Wiecha, Aurélie Lecestre, Nicolas Mallet, Guilhem Larrieu. Pushing the limits of optical information storage using deep learning. 2018. ⟨hal-01850258⟩



Record views