ML Anthology

Differentiable Image Parameterizations

Alexander Mordvintsev, Nicola Pezzotti, Ludwig Schubert, Chris Olah
Distill 2018
doi:10.23915/distill.00012 /distill/2018/mordvintsev2018distill-differentiable/

Abstract

Distill articles are interactive publications and do not include traditional abstracts. This summary was written for the ML Anthology. Explores how alternative mathematical representations of images—including Fourier transforms, compositional pattern-producing networks, and 3D rendering—can improve neural network optimization for visualization and artistic applications.

Distill Code Semantic Scholar

Cite

Text

Mordvintsev et al. "Differentiable Image Parameterizations." Distill, 2018. doi:10.23915/distill.00012

Markdown

[Mordvintsev et al. "Differentiable Image Parameterizations." Distill, 2018.](https://mlanthology.org/distill/2018/mordvintsev2018distill-differentiable/) doi:10.23915/distill.00012

BibTeX

@article{mordvintsev2018distill-differentiable,
  title     = {{Differentiable Image Parameterizations}},
  author    = {Mordvintsev, Alexander and Pezzotti, Nicola and Schubert, Ludwig and Olah, Chris},
  journal   = {Distill},
  year      = {2018},
  doi       = {10.23915/distill.00012},
  url       = {https://mlanthology.org/distill/2018/mordvintsev2018distill-differentiable/}
}