University of Oulu

Hauptmann, Andreas; Adler, Jonas (2020): On the unreasonable effectiveness of CNNs. TechRxiv. Preprint.

On the unreasonable effectiveness of CNNs

Saved in:
Author: Hauptmann, Andreas1,2; Adler, Jonas3
Organizations: 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
Format: preprint
Version: submitted version
Access: open
Online Access: PDF Full Text (PDF, 0.8 MB)
Persistent link:
Language: English
Published: TechRxiv, 2020
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.

see all

DOI: 10.36227/techrxiv.12761951.v1
Field of Science: 111 Mathematics
113 Computer and information sciences
Funding: 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
Detailed Information: 312123 (Academy of Finland Funding decision)
Copyright information: © 2020 The Authors. CC BY 4.0.