Jitendra Malik: Computer Vision | Lex Fridman Podcast #110

50 thoughts on “Jitendra Malik: Computer Vision | Lex Fridman Podcast #110”

1. I really enjoyed this conversation with Jitendra. Here's the outline:
   0:00 – Introduction
   3:17 – Computer vision is hard
   10:05 – Tesla Autopilot
   21:20 – Human brain vs computers
   23:14 – The general problem of computer vision
   29:09 – Images vs video in computer vision
   37:47 – Benchmarks in computer vision
   40:06 – Active learning
   45:34 – From pixels to semantics
   52:47 – Semantic segmentation
   57:05 – The three R's of computer vision
   1:02:52 – End-to-end learning in computer vision
   1:04:24 – 6 lessons we can learn from children
   1:08:36 – Vision and language
   1:12:30 – Turing test
   1:16:17 – Open problems in computer vision
   1:24:49 – AGI
   1:35:47 – Pick the right problem

2. Did Jitendra say " tabular …learning in a supervised world". can someone repeat the term/phrase again as i could not understand the full term he used and neither can i find it on google. Thank you

3. children do need labels. I spend ages with my children, pointing and naming. It is a normal and vital part of life, especially in the first 3 years. It is about 90% of conversation, labeling stuff.

4. 38:46 "We should really be collecting data of the type that a child experiences." Researcher Deb Roy did this in 2011, filming his baby's entire early life. I think he primarily used it to track language acquisition; I've always wondered what would happen if you played it all back to a baby robot.

5. Nice yo

6. wow

7. 1:16:00 the blind assistant could be like a virtual Amelie Poulain 😀 Could be exhausting over time ^^
   https://www.youtube.com/watch?v=MOD11gnTKyA

8. I have a dream to talk to you.

9. I think we should use tiktok, YouTube, Snapchat…data for visualizing A.I before getting it on the road 17:50

10. Humans are black boxes too. Good point.

11. Thanks Lex ❤

12. Always ready for a funeral

13. I presume that Malek shared some high octane ganja with fridman because during the introduction fridman presented to be uncharacteristically less Russian, almost to appear happy.

14. Awesome interview, Lex, as always!

    Connected to the evolutionary discussion, Jordan Peterson lectures give great insights on the current theories of human and animal minds. It was particularly surprising to me how much action is in the hypothalamus, to the point that an animal can be quite functional with the cortex removed, and just acting based on the hypothalamus. I believe a discussion between you and Jordan would be super entertaining and insightful for the audience.

    Reference: Youtube video "2017 Maps of meaning 05: story and metastory (Part 1)", timestamp 1h 40m 23s.

    https://m.youtube.com/watch?v=RudKmwzDpNY&feature=youtu.be&t=1h40m23s

15. "humans are not fully explainable". Interesting (counter)point.

16. This conversation is probably your best.

17. Thanks you Lex Fridman, helps me understanding Computer Vision

18. Great! Eventually you'll have to interview Linus Torvards and Richard Stallman

19. Go back to your country

20. I remember when I first started driving I was a lot more naieve about the number of things that could go wrong. For instance, I was waiting at the head of a line at a red light and went as soon as it turned green, making a left turn. There was a line of cars to the right waiting to make their left turn. The middle lane, which was obscured by that line of cars, had an individual who was speeding and ran the red light. Almost totaled the truck. As I was sitting there in the middle of the intersection with a disabled vehicle, I realized the mistake I made in assuming that the obscured lane wasn't a danger.

21. Without a Soul a machine cant see a reality. Not because it has no camera but because it only does what its programed to do.

22. Hi Lex, you should get Sam Harris on the show. Hes extremely well spoken on the topic of AI and even Elon says hes great and understands the future of AI really well. He would be a really popular guest.

23. If autonomous highway driving can be solved, that's huge for trucking. Send trucks across the highways to depots, have drivers complete the last half hour.
    Nice for longer commuters too.

24. Any infomation on the Google Quantum Computer??? :):):)

25. Next Podcast with Andrej Karpathy please.

26. It amazes me how many purportedly smart people are so grotesquely stupid when it comes to FSD. (You among them, my beloved Lex.)

    Level 5 autonomy is an idiotic idea forwarded by idiots for idiots. ignore it.

    Luckily Microsoft was unable to make billions of dollars and rampantly advance computer adoption and evolution by selling operating systems because they never made one that was perfect. Can't have an operating system until it is perfect.

    Please stop with this idiotic non logic.

    FSD need not ever be perfect. it needs to be actuarily safer than humans and that is not a very high bar.

    Nothing rational says an autonomous car cannot raise its hand and ask for help, either from someone in the car or someone at Quintuple A (American Autonomous Automotive Assistance Association) who drops into the car virtually from their trailer in Omaha and gets the car out of a tricky situation.

    Meteors will fall from the sky and kill people in cars, lightning will strike cars and kill people. trees will fall onto the highway and kill people, rocks will fall off of trucks and kill people, drunk drivers will run red lights and kill people.

    Stop talking about level 5 autonomy. it is a transient stupidity which will die soon.

27. Lex, I am surprised to hear you expressing so much doubt regarding autonomous driving. Especially after watching your interview with Jim Keller. Also you must have seen the video out there of teslas driving themselves on and off the 280 freeway, passing cars and being passed changing lanes negotiating intersections on the Sandhill Road. There’s also this thing about autonomous driving having to be perfect. I get this impression from people; That they believe autonomous driving can never have a mistake. Must always has to be perfect. If someone gets injured, or killed you have to throw it out. I think the more realistic way to look at it, and the way that Elon looks at it – it’s like this, when autonomous driving is 100 times safer than having humans behind the wheel, that will be a great achievement. Why would you ever have a human behind the wheel after that?

28. Auto pilot uses radar and sonar as well as its cameras. I would love to hear Jim Keller or Elon debating this guy about whether or not autonomous driving can be accomplished.

29. Consciousness explained. https://www.amazon.com/-/es/Guillermo-Brand/dp/3846577820

30. This was amazing, always love to hear Prof. Jitendra Malik. Could you please schedule a discussion with Jeff Dean as well?

31. Is it possible to create a network that can understand general motion much like how a human understands on a coarse level, inertia? Consider a Tesla that had a computer-aided model of the world outside the car that simulated inertial moments for objects, this would be another step in the right direction towards a spatial awareness that can accurately map objects and their likely trajectory. Humans can learn what skateboarders do with relatively little data because we understand general motion

32. Can u do a podcast with Hofstadter, that would be great

33. We need to raise robot children.

34. Excellent conversation Lex. I feel the podcast has started exploring a lot more territories outside of AI but I am glad you brought it back to computer vision and deep tech. The demarcation between images and video is excellent. This is what I come here for!

35. Could you invite Prof. David Mumford. An amazing researcher with deep math background and who later on did vision. He has done very interesting work, everything from Mumford Shah functional, his paper on statistics of images, theory of shapes and patterns.

36. I posted this comment for Joe that I am certain no-one will ever read…. maybe you will Brother/doctor/strong like Russian LEX FRIDMAN -LOVE U TOO LEX (am I crazy or is this the answer AI will come to eventually?): "Hey Joe, I love you my brother! Think of "DARK ENERGY/MATTER" as simply particles like Photons (force carriers) that only exist at a speed faster than photons and that is why us humans can not "see" it yet. Think of gravity as the only force that can interact with particles at "BOTH SPEEDS" (i.e. photons only exists at about 3 x 10(to the eight) meters per second or less depending on the medium, but "dark" faster than light particles exists at some much faster quantized speed (tachyon)). Think of BLACK HOLES as as tornados acting as particle accelerators taking known force carriers like photons and swirling them up to some, as yet undiscovered, faster-than-light quantized speed where particles become invisible to us yet still interacts with gravity. I have the mathematics to prove it but just like this comment, nobody will ever read it. See Joe, all this "dark matter/energy" bullshit is really very simple. Love what you do bro and THANK YOU JOE ROGAN for the free education you provide my friend!"

37. @1:29:29 golden words! the problems of safety, biases, risks are today. The bigger problems NOBODY is paying enough attention to, is the governance of AI that will be in your brain Lex and Jitendra. And your children. I am still surprised that no one is giving it enough attention. The video with Ben he mentioned some of those problems and how we are building resolutions for those. but we need an army. . Point is, I am NOT being negative here, quiet the opposite, AI can be fabulous for humanity but until then the governance is not being taken seriously. Attack from within… Pick a single entity you are comfortable with in taking over your "free will"… Or what we are proposing, "Atonomous Decentralized Governance" so no one can repurpose your extended brain/ AI without your control. . Today your phone is your extended brain. Tomorrow will be a lot closer to your brain.

38. https://youtu.be/i5L9gHsqSQk

39. I guess the only place left in the universe for it innovation is radiation hardened hardware

40. https://youtu.be/XSEPwokZmRQ

41. Pretty much if you haven't dumped every penny of federal reserve notes into physical silver, buried it like a real life pirate then secured food for at least a year …… your an idiot. Honestly physical silver is the only thing that's real . If you dont hold it and cant defend it . It's not yours

42. Fix the lighting. Jitendra shows up in well-lit frame and Lex in the different colored frames. Otherwise content is good.

43. I really like talks about AGI. Specifically, how to build it.

44. Lex Fridman, its hard to keep up with you lol! Lovely interviews. Hope ur fine.

45. Lex, go high! Try to interview Noam Chomsky on AI (again). Sad that Josef Weizenbaum (Eliza) is not around any more.

46. Thanks for the wonderful videos, Lex, lots of love! Can we get Naval Ravikant, Jeffrey Sachs on the Lexcast? That'd break the intellectual part of the net!

47. 1:19:54
    https://arxiv.org/abs/1811.10519
    https://arxiv.org/abs/1910.00287

48. What a fantastic speaker Jitendra is! Thank you for meeting us with him. That was truly inspiring talk. I wish I had mentors such as him. Though I think vision is a bit overestimated. For example blind people are just as intelligent as people who see. Which points that the human brain is really a multi-sensory device. I.e. it doesn't just use one type of sensory input, in contrary, it combines all the available channels to get the best model of the universe. So maybe it will be a multi-channel recognition that will be the big breakthrough. Anyway, thank you for this stimulating conversation.

49. Thanks Lex

50. Where is Demis Hassabis?

Comments are closed.