On the unreasonable effectiveness of CNNs
Hauptmann, Andreas; Adler, Jonas (2020-08-07)
Hauptmann, Andreas
Adler, Jonas
TechRxiv
07.08.2020
Hauptmann, Andreas; Adler, Jonas (2020): On the unreasonable effectiveness of CNNs. TechRxiv. Preprint. https://doi.org/10.36227/techrxiv.12761951.v1
https://creativecommons.org/licenses/by/4.0/
© 2020 The Authors. CC BY 4.0.
https://creativecommons.org/licenses/by/4.0/
© 2020 The Authors. CC BY 4.0.
https://creativecommons.org/licenses/by/4.0/
Julkaisun pysyvä osoite on
https://urn.fi/URN:NBN:fi-fe2020082663179
https://urn.fi/URN:NBN:fi-fe2020082663179
Tiivistelmä
Abstract
Deep learning methods using convolutional neural networks (CNN) have been successfully applied to virtually all imaging problems, and particularly in image reconstruction tasks with ill-posed and complicated imaging models. In an attempt to put upper bounds on the capability of baseline CNNs for solving image-to-image problems we applied a widely used standard offthe- shelf network architecture (U-Net) to the “inverse problem” of XOR decryption from noisy data and show acceptable results.
Kokoelmat
- Avoin saatavuus [32026]