Editing Glossary
The edit can be undone. Please check the comparison below to verify that this is what you want to do, and then publish the changes below to finish undoing the edit.
Latest revision | Your text | ||
Line 36: | Line 36: | ||
= Appearance and voice theft = | = Appearance and voice theft = | ||
Appearance is thieved with [[digital look-alikes]] and voice is thieved with [[digital sound-alikes]]. These are new and very extreme forms of identity theft. Ban covert modeling and possession and doing anything with a model of a human's voice, but don't ban the [[Adequate Porn Watcher AI (concept)]]. | Appearance is thieved with [[digital look-alikes]] and voice is thieved with [[digital sound-alikes]]. These are new and very extreme forms of identity theft. Ban covert modeling and possession and doing anything with a model of a human's voice, but don't ban the [[Adequate Porn Watcher AI (concept)]]. | ||
---- | ---- | ||
Line 77: | Line 73: | ||
* Covertly modeling the '''human voice''' | * Covertly modeling the '''human voice''' | ||
There is work ongoing to model e.g. '''human's style of writing''', but this is probably not as drastic a threat as the covert modeling of appearance and of voice. | There is work ongoing to model e.g. '''human's style of writing''', but this is probably not as drastic a threat as the covert modeling of appearance and of voice. | ||
---- | ---- | ||
Line 156: | Line 146: | ||
= Generative adversial network = | = Generative adversial network = | ||
[[File:Woman | [[File:Woman 7.jpg|alt=An image generated by StyleGAN, a generative adversarial network (GAN), that looks deceptively like a portrait of a young woman.|thumb|250x250px|An image generated by [[w:StyleGAN]], a [[w:generative adversarial network]] (GAN), that looks deceptively like a portrait of a young woman.]] | ||
{{Q|A '''generative adversarial network''' ('''GAN''') is a class of [[w:machine learnin|g]] systems. Two [[w:neural network|neural network]]s contest with each other in a [[w:zero-sum game|zero-sum game]] framework. This technique can generate photographs that look at least superficially authentic to human observers,<ref name="GANs">{{cite arXiv |eprint=1406.2661|title=Generative Adversarial Networks|first1=Ian |last1=Goodfellow |first2=Jean |last2=Pouget-Abadie |first3=Mehdi |last3=Mirza |first4=Bing |last4=Xu |first5=David |last5=Warde-Farley |first6=Sherjil |last6=Ozair |first7=Aaron |last7=Courville |first8=Yoshua |last8=Bengio |class=cs.LG |year=2014 }}</ref> having many realistic characteristics. It is a form of [[w:unsupervised learning|unsupervised learning]]]].<ref name="ITT_GANs">{{cite arXiv |eprint=1606.03498|title=Improved Techniques for Training GANs|last1=Salimans |first1=Tim |last2=Goodfellow |first2=Ian |last3=Zaremba |first3=Wojciech |last4=Cheung |first4=Vicki |last5=Radford |first5=Alec |last6=Chen |first6=Xi |class=cs.LG |year=2016 }}</ref>|Wikipedia|[[w:generative adversarial network|generative adversarial networks]]}} | {{Q|A '''generative adversarial network''' ('''GAN''') is a class of [[w:machine learnin|g]] systems. Two [[w:neural network|neural network]]s contest with each other in a [[w:zero-sum game|zero-sum game]] framework. This technique can generate photographs that look at least superficially authentic to human observers,<ref name="GANs">{{cite arXiv |eprint=1406.2661|title=Generative Adversarial Networks|first1=Ian |last1=Goodfellow |first2=Jean |last2=Pouget-Abadie |first3=Mehdi |last3=Mirza |first4=Bing |last4=Xu |first5=David |last5=Warde-Farley |first6=Sherjil |last6=Ozair |first7=Aaron |last7=Courville |first8=Yoshua |last8=Bengio |class=cs.LG |year=2014 }}</ref> having many realistic characteristics. It is a form of [[w:unsupervised learning|unsupervised learning]]]].<ref name="ITT_GANs">{{cite arXiv |eprint=1606.03498|title=Improved Techniques for Training GANs|last1=Salimans |first1=Tim |last2=Goodfellow |first2=Ian |last3=Zaremba |first3=Wojciech |last4=Cheung |first4=Vicki |last5=Radford |first5=Alec |last6=Chen |first6=Xi |class=cs.LG |year=2016 }}</ref>|Wikipedia|[[w:generative adversarial network|generative adversarial networks]]}} | ||
Line 209: | Line 199: | ||
'''Media forensics''' deal with ascertaining genuinity of media. | '''Media forensics''' deal with ascertaining genuinity of media. | ||
{{Q|Wikipedia does not have an article | {{Q|Wikipedia does not have an article on [[w:Media forensics]]|juboxi|2019-04-05}} | ||
---- | ---- | ||
Line 250: | Line 240: | ||
Past: As of 2020-11-19 Wikipedia does not have an article on '''relighting'''. | Past: As of 2020-11-19 Wikipedia does not have an article on '''relighting'''. | ||
---- | ---- | ||
Line 278: | Line 257: | ||
See '''[[wikidata:]]''' for translations, descriptions and links to WMF wikis about speech syntheses. | See '''[[wikidata:]]''' for translations, descriptions and links to WMF wikis about speech syntheses. | ||
---- | ---- | ||
Line 311: | Line 282: | ||
---- | ---- | ||
= References = | = References = |