How computers are learning to be creative | Blaise Agüera y Arcas

How computers are learning to be creative | Blaise Agüera y Arcas

We’re on the edge of a new frontier in art and creativity — and it’s not human. Blaise Agüera y Arcas, principal scientist at Google, works with deep neural networks for machine perception and distributed learning. In this captivating demo, he shows how neural nets trained to recognize images can be run in reverse, to generate them. The results: spectacular, hallucinatory collages (and poems!) that defy categorization. “Perception and creativity are very intimately connected,” Agüera y Arcas says. “Any creature, any being that is able to do perceptual acts is also able to create.”

TEDTalks is a daily video podcast of the best talks and performances from the TED Conference, where the world’s leading thinkers and doers give the talk of their lives in 18 minutes (or less). Look for talks on Technology, Entertainment and Design — plus science, business, global issues, the arts and much more.
Find closed captions and translated subtitles in many languages at http://www.ted.com/translate

Follow TED news on Twitter: http://www.twitter.com/tednews
Like TED on Facebook: https://www.facebook.com/TED

Subscribe to our channel: http://www.youtube.com/user/TEDtalksDirector

50 Comments

  1. BEATS BYMANOLO on September 17, 2019 at 7:58 pm

    over explained



  2. Odin on September 17, 2019 at 7:58 pm

    Это аху**но просто. В моем сознании произошел переворот, это уже реально не шуточный ИИ! К тому же это не так уж и сложно, сколько всего можно сделать на основе этой технологии!!



  3. TheTarrMan on September 17, 2019 at 7:58 pm

    They bottled creativity.



  4. DWNtoERTH on September 17, 2019 at 7:59 pm

    If I ever attended a ted talk I would be perpetually nodding in agreement in the off chance that the camera panned to me. I would look engaged and intelligent. Hopefully people on the internet would see me and then would think I was smart enough to attend said Ted talk.



  5. 김동민 on September 17, 2019 at 8:02 pm

    If i had a lot of money , i would have put my money this area.



  6. neumann sh on September 17, 2019 at 8:02 pm

    introduction to ml



  7. 코다리 on September 17, 2019 at 8:03 pm

    9:25



  8. Somto Achu on September 17, 2019 at 8:03 pm

    if i had any doubt of what am doing in my masters its cleared am so doing AI



  9. 和輝Kazuki on September 17, 2019 at 8:03 pm

    11:42 waits for clap. Awkwardly continues talking and stuttering.



  10. Rachna Gupta on September 17, 2019 at 8:09 pm

    That is a very layman explanation of Neural Network. A very good one too.



  11. hichem RE on September 17, 2019 at 8:09 pm

    one day we will arrive at a time were human would have no place for creating art AI would generate movies music poems etc and what’s magical about art would disapear making it less beautiful making less art :/ what a depressing thing to happen



  12. M. Oliveira on September 17, 2019 at 8:10 pm

    This is an amazing human creativity . I always wonder understand what computers "draw" if they have a complex creative algoritm… So…this is the answer. Thank you very much. Fantastic work!



  13. ThisGuy on September 17, 2019 at 8:11 pm

    its always funny when people think creativity is kinda intutive magic out of the blue when its just rationlity with sprinkles



  14. colin schabel on September 17, 2019 at 8:12 pm

    We are so close to a utopian society made possible by technology. The only problem is I’m going to miss it



  15. Not You on September 17, 2019 at 8:13 pm

    It’s like the same art style that Pouff uses in his videos, you should go check him out, he has some pretty trippy content!



  16. bagumondigi on September 17, 2019 at 8:14 pm

    Is this open source ?



  17. Thor on September 17, 2019 at 8:17 pm

    Our lives are going to get so much better…!!



  18. Arthur Kor on September 17, 2019 at 8:20 pm

    8:48 Bless you!



  19. Nikolas Ioannou on September 17, 2019 at 8:20 pm

    I tried this and ended up generating adversarial images. Anyone else? Or anyone who did it successfully?



  20. Seb le Frenchie on September 17, 2019 at 8:20 pm

    I knew these things before thanks to a project and tbh this guy managed to explain it in an accessible way. Congratulations 🙂



  21. Jasper on September 17, 2019 at 8:20 pm

    there’s literally no other simulation of psychedelic visuals that even comes remotely close with the real experience other than this technology, and it should come as no surprise since it’s functioning the same way your brain is. we’ll come to see how similar the artificial brain is to our own soon. we don’t know much about this kind of learning or psychedelics but it doesn’t take a genius to see there’s huge parallels and that this is a fucking cool time to be alive.



  22. Rodrigo Neves on September 17, 2019 at 8:21 pm

    Este vídeo mostra um a notável investigação para conhecer como a percepção funciona e do modo como a AI replica todo o processo. Mas para mim as extraordinárias imagens mostradas não podem explicar o processo criativo a que Miguel Angelo se referiu. A arte é em si como o cosmo, um mistério que também ainda não se sabe para que serve. Gostaria de poder colaborar convosco: Rodrigo Ollero – rodrigo.ollero@sapo.pt



  23. Ali Tahrei-Shalmani on September 17, 2019 at 8:21 pm

    It explains to me why we dream in the way we dream.
    Our brain regenerates the image of things that it is processing while we are sleeping.
    and sometimes it records them and sometimes it feeds itself with the result.
    Now I understand my dreams.



  24. ФashionLAB on September 17, 2019 at 8:23 pm

    Очень заинтересовало ,буду изучать!)



  25. Pixelated Warrior on September 17, 2019 at 8:25 pm

    How did he make this boring for 10 minutes up until he showed the actual “art”



  26. Exit Paradise on September 17, 2019 at 8:26 pm

    OG mac users still got the backlit apple #100



  27. Vanilla Thunder on September 17, 2019 at 8:31 pm

    Such a great and entertaining explanation of the topic! Thank you.



  28. ZechsMerquise73 on September 17, 2019 at 8:35 pm

    Can anyone tell me where to find the backpack poetry neural network?



  29. F Lash on September 17, 2019 at 8:36 pm

    1 fkin question…………. Why ??



  30. Florian 2 on September 17, 2019 at 8:37 pm

    Depressing, meaningless rot.



  31. Robert Denham on September 17, 2019 at 8:38 pm

    Only a.i will get this: "to me to me to me you are to me to me to me."



  32. Francesco Stefani on September 17, 2019 at 8:38 pm

    Now it can kill us creatively 😀



  33. metamaggot on September 17, 2019 at 8:40 pm

    lsd and fractals lol



  34. Бахтияр Жакупов on September 17, 2019 at 8:40 pm

    SkyNet is close ) It s a matter of time



  35. MR. ARTROBOT on September 17, 2019 at 8:41 pm

    Makes me think this is what drugs are doing to our brains



  36. Sakthees Waran on September 17, 2019 at 8:42 pm

    14:50 I LOVE THIS (A.I LUNATIC FRACTALS )



  37. Exit Paradise on September 17, 2019 at 8:42 pm

    it’s amazing to me that the people (or, whoever) wrote the bible was talking about this similar thing. it’s like a viewpoint from within the mind… have to not read it literally to see this though



  38. wbx on September 17, 2019 at 8:43 pm

    Take lsd see computer art 12:10



  39. come4pvp on September 17, 2019 at 8:43 pm

    Could the multiple image pattern comes from down sampling by pooling operation?



  40. Marco Costa on September 17, 2019 at 8:44 pm

    If humans don’t want to be machines, why would the opposite be true?



  41. вовка шилик on September 17, 2019 at 8:45 pm

    nobody:
    neural networks:
    LSD



  42. Mrs. Jones on September 17, 2019 at 8:45 pm

    The patterns in the art that AI art is composed of, looks similar to the surface of the brain.



  43. Sakthees Waran on September 17, 2019 at 8:48 pm

    9:50 SO OPTIMIZATION IS ALSO SOLVING WITHOUT ANY TAKING ACTION ON COEFFICIENTS ARE THERE SIMULTANEOUS OPTIMIZATION LIKE SIMULTANEOUS EQUATION SOLVING CAN ANY ONE GIVE ME SOME EXAMPLES



  44. Quality Shit Edit on September 17, 2019 at 8:48 pm

    I’m sorry, deep mind just looks wrong.



  45. Red Star on September 17, 2019 at 8:50 pm

    This is not CREATIVE in any shape or form.



  46. Archive Studios on September 17, 2019 at 8:52 pm

    We dont need AI -we need jobs. Robots leading humans is dumber than Trump



  47. shakazed on September 17, 2019 at 8:52 pm

    One of the best talks I’ve seen.



  48. mikeyb10supra on September 17, 2019 at 8:53 pm

    I didnt know Lionel Messi knows AI



  49. Jake Soulvie on September 17, 2019 at 8:53 pm

    They’re creative because they’re in a messy environment. duh



  50. Denis Vladimirovich on September 17, 2019 at 8:55 pm

    Very nice, thanks for the lecture 🙂