On the unreasonable effectiveness of CNNs
|Author:||Hauptmann, Andreas1,2; Adler, Jonas3|
1Research Unit of Mathematical Sciences; University of Oulu, Oulu, Finland
2Department of Computer Science; University College London, London, United Kingdom
3KTH – Royal Institute of Technology, Stockholm Sweden. He is currently with DeepMind, London, UK
|Online Access:||PDF Full Text (PDF, 0.8 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2020082663179
|Publish Date:|| 2020-08-26
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.
|Field of Science:||
113 Computer and information sciences
This work was partially supported by the Academy of Finland Project 312123 (Finnish Centre of Excellence in Inverse Modelling and Imaging, 2018–2025) and the CMIC-EPSRC platform grant (EP/M020533/1)
|Academy of Finland Grant Number:||
312123 (Academy of Finland Funding decision)
© 2020 The Authors. CC BY 4.0.