Machine learning porn
From The Art and Popular Culture Encyclopedia
(Difference between revisions)
| Revision as of 21:45, 15 August 2017 Jahsonic (Talk | contribs) ← Previous diff |
Revision as of 12:37, 26 February 2018 Jahsonic (Talk | contribs) Next diff → |
||
| Line 10: | Line 10: | ||
| *[[Reverse engineering]] | *[[Reverse engineering]] | ||
| *[[Scunthorpe problem]] | *[[Scunthorpe problem]] | ||
| + | *[[Google censorship]] | ||
| {{GFDL}} | {{GFDL}} | ||
Revision as of 12:37, 26 February 2018
|
Related e |
|
Featured: |
Machine learning porn are images that are not pornographic but are false positives recognized by "adult filters" as pornography. Images in this category have been created by Gabriel Goh and Jake Elwes.
- "A convolutional neural network (shown thousands of images to teach itself to classify) has been trained using Yahoo’s explicit content model for finding pornography in their search engines, which is then back engineered to generate pornography from scratch (inspiration from Gabriel Goh)."--Jake Elwes[1]
See also
Unless indicated otherwise, the text in this article is either based on Wikipedia article "Machine learning porn" or another language Wikipedia page thereof used under the terms of the GNU Free Documentation License; or on research by Jahsonic and friends. See Art and Popular Culture's copyright notice.
