At the beginning of the universe, all was darkness – until the first organisms developed vision, which set off an explosion of life, learning and progress. AI pioneer Fei-Fei Li says a similar moment is about to happen for computers and robots. She shows how machines are gaining “spatial intelligence” – the ability to process visual data, make predictions and act on those predictions – and shares how this could enable AI to interact with people in the real world. If you enjoy watching TED talks like this, become a TED member to support our mission of spreading ideas: Follow TED! X: Instagram: Facebook: LinkedIn: TikTok: The TED Talks channel features talks, performances and original series from the world’s leading thinkers and creators. Subscribe to our channel for videos on…

By admin

35 thoughts on “With Spatial Intelligence, AI Will Understand the Real World | Fei-Fei Li | TED”
  1. 00:06 Evolution of sight led to understanding and diversity in Cambrian explosion
    02:09 Advancements in computer vision and artificial intelligence
    03:59 Advancements in generative AI algorithms powering new possibilities.
    05:45 Spatial intelligence links perception with action
    07:28 Advancements in spatial intelligence enabling 3D representation from images.
    09:28 Spatial intelligence enables machines to interact in 3D worlds.
    11:21 AI in healthcare improves patient outcomes and reduces medical staff burnout.
    13:19 The full potential of AI will be realized with spatial intelligence.
    Crafted by Merlin AI.

  2. Wonderful talk. Fei Fei Li is deservedly well known for her leadership in the "big data" shift of AI. Her "Worlds I See" book is a terrific read about challenges and fortitude in her life. For more on the hypothesis about the Cambrian explosion, see Andrew Parker's book "In the Blink of an Eye".

  3. So far we have an exponentially increasing carbon footprint to fuel AI. What we get are cat videos. Can't wait until the incentive changes to do more, but with increasingly energy efficient GPUs/ energy sources.

  4. This is such a disturbing take. As someone who unfortunately works parallel to GEOINT, this isn’t an advancement, it is overtly a weapon. The only use case driving this is surveillance, policing, and military operations. If you doubt this, look up where esri, the world leader in GIS, gets their funds. Spoiler: it’s the Department of Defense.

  5. I think one of the biggest pitfalls with AI is that people imagine intelligence and sentience as some kind of magical properties that just appear in a very special way, but I think it's most likely that they are gradual properties, emerging from gradual performance improvements in seemingly underwhelming areas.

  6. Hello Ted Talkks. I hope this comment find s you well. I am writing you today as a fellow Theodore and tender of Ted Media in proposition of an idea. David Oshry once said "great two minds think alike the better" and so I think we should clonk our skulls toghether and colloborate upon. we could make history. I'll even let you be the one to upload the video. thank you ted, love ted.

  7. I've never listened to a lecture that so clearly will prove in time to have been a super-villain monologuing.
    I think James Bond or Batman will get us out of this one… but I'm not certain.

  8. GIGO! With all do respect to the speaker, AI will never know more than what we know. We use to call this type of hype, vapor ware. 🙏💪🌏🌎🌍❤️🇺🇸🖖

  9. Looking deep in the AI models you can find the source code. We have looked extensibly into the brain but guess what. No code found !! Having AI (AI certainly is a misnomer) to try to imitate the brain to what? I thing there is a dead end coming soon

  10. I, my lab, my students, my colleagues… Even someone with a contribution that matched that of Newton, Euler, and Einstein combined make such a shamelessly copious number of self-references.

Leave a Reply

Your email address will not be published. Required fields are marked *