Monday, April 29, 2024
Latest:
Videos

Future Computers Will Be Radically Different (Analog Computing)

Artis Modus



Veritasium

Visit https://brilliant.org/Veritasium/ to get started learning STEM for free, and the first 200 people will get 20% off their annual premium subscription. Digital computers have served us well for decades, but the rise of artificial intelligence demands a totally new kind of computer: analog.

Thanks to Mike Henry and everyone at Mythic for the analog computing tour! https://www.mythic-ai.com/
Thanks to Dr. Bernd Ulmann, who created The Analog Thing and taught us how to use it. https://the-analog-thing.org
Moore’s Law was filmed at the Computer History Museum in Mountain View, CA.
Welch Labs’ ALVINN video: https://www.youtube.com/watch?v=H0igiP6Hg1k

▀▀▀
References:
Crevier, D. (1993). AI: The Tumultuous History Of The Search For Artificial Intelligence. Basic Books. – https://ve42.co/Crevier1993
Valiant, L. (2013). Probably Approximately Correct. HarperCollins. – https://ve42.co/Valiant2013
Rosenblatt, F. (1958). The Perceptron: A Probabilistic Model for Information Storage and Organization in the Brain. Psychological Review, 65(6), 386-408. – https://ve42.co/Rosenblatt1958
NEW NAVY DEVICE LEARNS BY DOING; Psychologist Shows Embryo of Computer Designed to Read and Grow Wiser (1958). The New York Times, p. 25. – https://ve42.co/NYT1958
Mason, H., Stewart, D., and Gill, B. (1958). Rival. The New Yorker, p. 45. – https://ve42.co/Mason1958
Alvinn driving NavLab footage – https://ve42.co/NavLab
Pomerleau, D. (1989). ALVINN: An Autonomous Land Vehicle In a Neural Network. NeurIPS, (2)1, 305-313. – https://ve42.co/Pomerleau1989
ImageNet website – https://ve42.co/ImageNet
Russakovsky, O., Deng, J. et al. (2015). ImageNet Large Scale Visual Recognition Challenge. – https://ve42.co/ImageNetChallenge
AlexNet Paper: Krizhevsky, A., Sutskever, I., Hinton, G. (2012). ImageNet Classification with Deep Convolutional Neural Networks. NeurIPS, (25)1, 1097-1105. – https://ve42.co/AlexNet
Karpathy, A. (2014). Blog post: What I learned from competing against a ConvNet on ImageNet. – https://ve42.co/Karpathy2014
Fick, D. (2018). Blog post: Mythic @ Hot Chips 2018. – https://ve42.co/MythicBlog
Jin, Y. & Lee, B. (2019). 2.2 Basic operations of flash memory. Advances in Computers, 114, 1-69. – https://ve42.co/Jin2019
Demler, M. (2018). Mythic Multiplies in a Flash. The Microprocessor Report. – https://ve42.co/Demler2018
Aspinity (2021). Blog post: 5 Myths About AnalogML. – https://ve42.co/Aspinity
Wright, L. et al. (2022). Deep physical neural networks trained with backpropagation. Nature, 601, 49–555. – https://ve42.co/Wright2022
Waldrop, M. M. (2016). The chips are down for Moore’s law. Nature, 530, 144–147. – https://ve42.co/Waldrop2016

▀▀▀
Special thanks to Patreon supporters: Kelly Snook, TTST, Ross McCawley, Balkrishna Heroor, 65square.com, Chris LaClair, Avi Yashchin, John H. Austin, Jr., OnlineBookClub.org, Dmitry Kuzmichev, Matthew Gonzalez, Eric Sexton, john kiehl, Anton Ragin, Benedikt Heinen, Diffbot, Micah Mangione, MJP, Gnare, Dave Kircher, Burt Humburg, Blake Byers, Dumky, Evgeny Skvortsov, Meekay, Bill Linder, Paul Peijzel, Josh Hibschman, Mac Malkawi, Michael Schneider, jim buckmaster, Juan Benet, Ruslan Khroma, Robert Blum, Richard Sundvall, Lee Redden, Vincent, Stephen Wilcox, Marinus Kuivenhoven, Clayton Greenwell, Michael Krugman, Cy ‘kkm’ K’Nelson, Sam Lutfi, Ron Neal

▀▀▀
Written by Derek Muller, Stephen Welch, and Emily Zhang
Filmed by Derek Muller, Petr Lebedev, and Emily Zhang
Animation by Ivy Tello, Mike Radjabov, and Stephen Welch
Edited by Derek Muller
Additional video/photos supplied by Getty Images and Pond5
Music from Epidemic Sound
Produced by Derek Muller, Petr Lebedev, and Emily Zhang

Source

Similar Posts

43 thoughts on “Future Computers Will Be Radically Different (Analog Computing)”

  2. the future of computing is likely not going to be "radically different", considering how much is still invested in an obscenely cope version of von neumann architecture, they made sure to crush that dream of anything different a good 50 years ago. now you're stuck with suboptimal GPUs by design and computers running a half dozen layers of virtualisation just to get anything working properly, analogue co-processing is adding another piece of trash on the fire

  13. This a wise analysis. Analog systems could be developed for passive functions like traffic lights, animal instructors, mall lighting systems, building automation system, flood monitor, disaster monitors, etc etc etc…

  16. Funnilly ehough, I was talking with ChatGPT about this a few weeks ago, before I saw this video. About neuromorphic and digital computing hybridization. Quite the amazing subject.

  28. 14:40
    What if they used Apples M1 or M2 "System on chips".. instead of GPU or whatever? more energy efficient, & the "ARM architecture" is supposed to be
    more simplified on the operation front than the X86 architecture most chips are built on, if I understand it correctly?

  29. We've misunderstood the use of digital systems. The key factors that will always exist should be noted.
    They are less susceptible to noise. – This makes digital optimal for long distance transmission.
    And, thus far, they support the most information dense storage mediums (for data with definite values like text and numbers).
    What we fail to acknowledge in this is that in digital systems, there is nothing between 1 and 0. But, in analog systems, there are an infinite number of steps between 1 and 0, and in the right application, they are valuable and important.
    Moreover, humans are NOT digital. Regardless of the firing (or not) of neurons being an "analog" to on and off, 1 or 0, the system they are built on is more variable and is actually a distinctly NON-digital system. The perception (inputs) and all of the various outputs of the human body are distinctly analog.
    You've shown us how the various AI systems and analog computers have been made to mimic the effects of neurons.
    I think that the scariest artificial intelligence will be the culmination of light based quantum ANALOG computers because it will be faster than the electrical based quantum analog computers that make up the biological human mind.

  32. I'm not sure given our trajectory that this will be used in the metaverse. I'm certain there's another major application for it now though…..

  38. Sooo you have to set the values you want to use, instead of the computer already understanding everything you can throw at it….But Analog is more customizable and efficient…so in all its more efficient for the task but less efficient for the user, in regards to digital tech which is very efficient for the user |Pause| when you consider the productivity of the information we consume on our phones, imop Analog wins(for individual productivity). Think about it…our phones waterboard us with useless junk and features that aren't even productive for war. BUT ANALOG IS INEXACT!

  41. Analog can be fast but runs are not precisely reproducible. With the industry wanting more speed, they are turning to AI, giving up on the human brain and making a conscious decision to accept that AI will make mistakes like humans do and the consequences will sometimes be disastrous.

Comments are closed.

WP2Social Auto Publish Powered By : XYZScripts.com