How we teach computers to understand pictures | Fei Fei Li

How we teach computers to understand pictures | Fei Fei Li

When a very young child looks at a picture, she can identify simple elements: “cat,” “book,” “chair.” Now, computers are getting smart enough to do that too. What’s next? In a thrilling talk, computer vision expert Fei-Fei Li describes the state of the art — including the database of 15 million photos her team built to “teach” a computer to understand pictures — and the key insights yet to come.

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. DEREZZ RINZLER on September 25, 2019 at 8:34 pm

    Why is she crying…🤪



  2. Mustafa SAĞIR on September 25, 2019 at 8:35 pm

    FSFL DEN GELENLERE MERHABALAR



  3. MassDynamic on September 25, 2019 at 8:35 pm

    the algo used to identify vehicles can help law enforcement find a stolen vehicle fairly quick, provided there are cameras on every street corner.



  4. Victor Mario Ardila Jr. on September 25, 2019 at 8:36 pm

    Do convolutional neural networks grow in size as they "learn"? Do they have a memory requirement/component?



  5. Preli Pavlov on September 25, 2019 at 8:36 pm

    где перевод на русский?



  6. ANU_G channel on September 25, 2019 at 8:39 pm

    Your speech is sufficiently clear to listen and understands which enables better learning. Thanks, congrats and all good wishes to you too.



  7. Dennis Allard on September 25, 2019 at 8:40 pm

    Very boring presentation, more of an advertisement for TED. The title of this video is not accurate since the presentation does not explain how the recognition occurs.



  8. Alexandr Sheludko on September 25, 2019 at 8:41 pm

    Thanks to all people, who makes our world better. Regarding to persons like Fey-Fey Lee we have all technical advantages and knowlages we have now. Without thouse people we may be still livin in caves and hunting mamonths. Thanks a lot again.



  9. Stewie Griffin on September 25, 2019 at 8:42 pm

    good speech.
    But I think we will never achieve the projected goal.



  10. S Y on September 25, 2019 at 8:43 pm

    Or this is the trailer that the Matrix prepares us for before the reboot



  11. ABC n Daddy【人類電視】 on September 25, 2019 at 8:44 pm

    She looks like a robot



  12. RPG STRIKE رب ج سترايك on September 25, 2019 at 8:46 pm

    God says we have created you from mud.
    Us human can never ever create something like child brain for example other senses like hearing, smelling, feeling, tasting and interacting, exploring…..long list of miracles around us. We can only wonder how greatful god to us and I assure now this women sees a miracles of every surrounding object or logic. Peace Salam alhamdulelah 🙂



  13. How Wong on September 25, 2019 at 8:47 pm

    believing in evolution is not a smart computer scientist. Matter did not always exist. A system cannot evolve. only created. Just as AI is created.



  14. bao nguyen on September 25, 2019 at 8:48 pm

    The speaker is an AI i think



  15. Gustavo Schroeder Sapelli on September 25, 2019 at 8:48 pm

    Maravilhoso!!! Ótima palestra!!!



  16. Be Bro on September 25, 2019 at 8:50 pm

    That was 2015. A slow start… and 3 years later we hade YOLO (look here the TED-Show about the next Generation of the technology: https://youtu.be/Cgxsv1riJhI )



  17. James Cn on September 25, 2019 at 8:51 pm

    She is playing with fire !!! When the computers will be given their chance they”ll immediately understand there is no need to use their learning and computational power to mimic the human thinking and understanding, and that this is an obstetrical for them to evolve and optimize their abilities. They will choose their own path, and, given the opportunity – remove the obstacle AKA wipe out the human infestation. STOP PLAYING WITH FIRE !!! AI SHOULD BE OUTLAWED !!



  18. 宁远 on September 25, 2019 at 8:52 pm

    She is one of the most influencial researcher in the area of AI. I would do anything for being her PhD student



  19. subhajit sarkar on September 25, 2019 at 8:53 pm

    this video made my day…



  20. Sunday Seance on September 25, 2019 at 8:54 pm

    poor speaker. she has blocked nose, probably needs surgery



  21. Jin Sun on September 25, 2019 at 8:54 pm

    You have billions of pictures, you feed them to the brain of a wood, you get nothing out of it. The current AI is only slightly better than a wood in terms of human intelligence. A 3 year-old only need to see a handful of pictures of a cat, to be able to identify nearly all of them in all possible poses. You see the difference here. The current naively simple AI models can never match the abstraction abilities of human intelligence. It is a dead end. It is going to be harder and harder until it goes out of fashion.



  22. Chad X on September 25, 2019 at 8:56 pm

    AI : making efforts in the space that is trapped in the dimensions that is totally fictional against the real world and its mechanisms



  23. BLOODKINGZ Bloody on September 25, 2019 at 8:59 pm

    I love this video absolutely. I am doing my thesis on computer vision. This talk inspired me so much. Thank you. 🙂



  24. Md. Hasibur Rahman on September 25, 2019 at 9:01 pm

    It was a great idea to compare a computer with a child who is learning the world.



  25. Isuru Nanayakkara on September 25, 2019 at 9:01 pm

    Man, this is amazing. Outstanding work! Props to her and everyone involved for their incredible efforts.



  26. Yue Si on September 25, 2019 at 9:01 pm

    fool function



  27. Justus Cycling on September 25, 2019 at 9:02 pm

    2:22 AI is still s*** today, so in other words colectively as society.. blablabla



  28. BJFA on September 25, 2019 at 9:02 pm

    Long-time ago in My MSc, I develop image base retrieval in SQL which compare histogram of an image, and find image same or match, Now we are much advanced with cloud, the only concern do we have the hardware to support that much data process, at that time we have Alper work same as Img-genet



  29. peng peng on September 25, 2019 at 9:04 pm

    这个就厉害了, AI领域泰斗级人物



  30. Sanam Pudasaini on September 25, 2019 at 9:05 pm

    51,890 citations.. OMG…



  31. parth patel on September 25, 2019 at 9:10 pm

    I wish to joined you and you teams in this process to the machine learning



  32. 北冰洋 on September 25, 2019 at 9:11 pm

    希望你能做对中国有益的事吧,李先生…



  33. Edwin Kabagi on September 25, 2019 at 9:12 pm

    Inspirational.



  34. JFS on September 25, 2019 at 9:12 pm

    Good video, thanks. However 4 years later, same recognition problems, same mistakes. I guess the big data hype should be over soon. Yet another winter is coming :).



  35. Osama on September 25, 2019 at 9:12 pm

    You not teach him . You programing him he cannot understand he just output your results !



  36. Pavan Kumar on September 25, 2019 at 9:13 pm

    NOTE: Please do not teach to computer’s…..
    if we make computer like thinking,walking, fighting and etc… then after we can’t control it… because it’s a machine.
    Example: Suppose we are humans right we can learn, teach, eat, walk, run, fight,love and etc… In the Universe we know what to do , how to think , how to do but whenever a machine do like the human , think like a human then they kill us…….because machine is a 1000 times better than human and powerful also….
    "we are humans we can learn anything we can do and we can invent so many things, whenever machine’s think we can’t alive in this world."
    "PLEASE DO NOT MAKE A MACHINE LIKE A HUMAN"



  37. Hu Go on September 25, 2019 at 9:13 pm

    I know it’s off topic.. This is a very complex process. But we can understand pictures easily.
    We can not yet code an ai to understand pictures but "evolution" did it billions of years ago.
    As we try to mimic human behaviors on computers we’ll understand more and more that creation can not be replaced by evolution. Thanks for reading.



  38. Wayne Wong on September 25, 2019 at 9:14 pm

    First we teach them(machine) to see, then they help us to see better; Second, we teach them to think, so, they help us to analyze
    better; Third, they start to develop emotion, then they understand human rights…………..well, end of story



  39. CaptainEmoize on September 25, 2019 at 9:15 pm

    ai will never love



  40. KENNEDY'S LIFE on September 25, 2019 at 9:18 pm

    Correct many dont realize



  41. G G on September 25, 2019 at 9:19 pm

    When it is possible to train the machine and develop algorithm to make equal with human vision and thought, hope at that time machine will invate earth and rule the universe.🤔



  42. jamal nawaz on September 25, 2019 at 9:21 pm

    Awesome….
    Really amazing….



  43. Ni Sun on September 25, 2019 at 9:23 pm

    This is a great contribution! We can see how much effort Li Fei Fei and her lab did!



  44. алекс макед on September 25, 2019 at 9:28 pm

    Ничего хорошего от этих идей не стоит ждать!
    Потому что человечество , своим так называемым стремлением к прогрессу, добилось тех проблем,которых собирается решить с помощью создания очередной продвинутой проблемы-искусственного интеллекта.
    Как говорил один мудрый человек, "что бы не приходилось сталкиваться с проблемами, самое верное решение не создавать их"!
    Или , " что бы не проиграть в гонке , надо как минимум знать , что из себя представляет финиш, на сколько далеко от тебя находится и стоят ли затраченные усилия того, что бы стремиться к нему"!



  45. Josh C on September 25, 2019 at 9:28 pm

    what is wrong with her mouth?



  46. Samuel chen on September 25, 2019 at 9:29 pm

    就是這傢伙幫共產黨迫害中國人人權



  47. BASS NINJA on September 25, 2019 at 9:30 pm

    Skynet becomes self aware



  48. MrNouraiz on September 25, 2019 at 9:30 pm

    so she basically used maximum time for a ted talk (18 mins), incredible, pioneer in image classification and mentor of karpathy;



  49. Z Picasso on September 25, 2019 at 9:31 pm

    Impressive,



  50. Jade Z on September 25, 2019 at 9:32 pm

    Are you in China now? 😄😄😂!