Difference between revisions of "Impressive advances in AI"
(Created page with "This page lists impressive results in machine learning. == Image processing == Online photorealistic portrait generator is available at [http://thispersondoesnotexist.com th...") |
|||
| (5 intermediate revisions by the same user not shown) | |||
| Line 5: | Line 5: | ||
Online photorealistic portrait generator is available at [http://thispersondoesnotexist.com thispersondoesnotexist.com]. | Online photorealistic portrait generator is available at [http://thispersondoesnotexist.com thispersondoesnotexist.com]. | ||
| − | Detect gayness from picture. | + | [https://imglarger.com/ imglarger.com] proposes super-resolution enhancement, while [http://bgeraser.com/ bgeraser.com] proposes background erasing. |
| + | |||
| + | [https://pdfs.semanticscholar.org/af30/a2394c620132884bb98c78b6b9e46c791482.pdf WangKosinski][https://scholar.google.ch/scholar?hl=en&as_sdt=0%2C5&q=Deep+neural+networks+are+more+accurate+than+humans+at+detecting+sexual+orientation+from+facial+images&btnG= 18] Detect gayness from picture. | ||
Detect heart beat rate from video. | Detect heart beat rate from video. | ||
| Line 14: | Line 16: | ||
[http://openaccess.thecvf.com/content_ICCV_2019/papers/Nirkin_FSGAN_Subject_Agnostic_Face_Swapping_and_Reenactment_ICCV_2019_paper.pdf NKH][https://dblp.org/rec/bibtex/journals/corr/abs-1908-05932 19] propose face swapping and reenactement techniques. | [http://openaccess.thecvf.com/content_ICCV_2019/papers/Nirkin_FSGAN_Subject_Agnostic_Face_Swapping_and_Reenactment_ICCV_2019_paper.pdf NKH][https://dblp.org/rec/bibtex/journals/corr/abs-1908-05932 19] propose face swapping and reenactement techniques. | ||
| + | |||
| + | [http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhou_Deep_Single-Image_Portrait_Relighting_ICCV_2019_paper.pdf ZHSJ][https://scholar.google.ch/scholar?hl=en&as_sdt=0%2C5&q=Deep+Single+Image+Portrait+Relighting&btnG= 19] propose re-lightening techniques. | ||
== Sound processing == | == Sound processing == | ||
| Line 20: | Line 24: | ||
[https://openai.com/blog/musenet/ Payne19] proposed MuseNet to create musical compositions. | [https://openai.com/blog/musenet/ Payne19] proposed MuseNet to create musical compositions. | ||
| + | |||
| + | [https://www.respeecher.com Respeecher] allows to create speeches in another person's voice. | ||
Google Duplex. | Google Duplex. | ||
| Line 46: | Line 52: | ||
Deep learning for symbolic math [https://arxiv.org/pdf/1912.01412 LampleCharton][https://dblp.org/rec/bibtex/journals/corr/abs-1912-01412 19] | Deep learning for symbolic math [https://arxiv.org/pdf/1912.01412 LampleCharton][https://dblp.org/rec/bibtex/journals/corr/abs-1912-01412 19] | ||
| + | |||
| + | == | ||
| + | |||
| + | [https://www.amazon.com/Clinical-Versus-Statistical-Prediction-Theoretical/dp/0963878492 Meehl54] list examples from 1954 where statistical computations suffice to outperform clinical predictions by doctors (to verify). | ||
Latest revision as of 23:10, 17 February 2020
This page lists impressive results in machine learning.
Contents
Image processing
Online photorealistic portrait generator is available at thispersondoesnotexist.com.
imglarger.com proposes super-resolution enhancement, while bgeraser.com proposes background erasing.
WangKosinski18 Detect gayness from picture.
Detect heart beat rate from video.
ZAO allows users to face swap from one picture, and become Di Caprio in Titanic.
JoPark19 propose a GAN to easily photoshop real images in milliseconds. Similar inpaintings by NVIDIA are available here.
NKH19 propose face swapping and reenactement techniques.
ZHSJ19 propose re-lightening techniques.
Sound processing
JZWWS+18 learns to synthesize voice from 5-second samples.
Payne19 proposed MuseNet to create musical compositions.
Respeecher allows to create speeches in another person's voice.
Google Duplex.
Natural language processing
RWAAC+19 proposed GPT2, which you can play with on talktotransformer.com.
LCRDJ18 achieved state-of-the-art translations without parallel data. They simply found a rotation of the word embeddings of two languages that make the embeddings fit nicely.
Games
AlphaGo, Alpha Zero.
AlphaStar.
Social skills
YKS15 showed that algorithms outperformed even close relatives at predicting an individuals' personality traits derived from a combination of relatives' judgments.
EIYSDH16 showed that algorithms could outperform naive humans at emotion classification based on images.
Problem solving
Deep learning for symbolic math LampleCharton19
==
Meehl54 list examples from 1954 where statistical computations suffice to outperform clinical predictions by doctors (to verify).
