user avatar
Reza Zadeh
@Reza_Zadeh
Founder CEO @Matroid. Adjunct Professor @Stanford. Early @Databricks. Focused on Machine Learning.
Stanford, CA
Joined November 2009
Posts
  • user avatar
    It's pretty awesome how dancing makes robots less intimidating. Looking forward to seeing more nontrivial Machine Learning on these robots. Credit: Boston Dynamics.
    00:00
  • user avatar
    When you use a 10 layer Deep Neural Network where Logistic Regression would suffice
    00:00
  • user avatar
    A makeshift submarine using IKEA food container & legos. I love the idea of magnets to transfer kinetic energy without breaking the seal. By BEC youtube.com/c/BrickExperim…
    00:00
  • user avatar
    00:00
  • user avatar
    "Sorry officer, my car has old version of TensorFlow, I'll update it tonight"
  • user avatar
    Just paid for the health insurance of my American employees. As a Canadian-Iranian with an EB-1 Green Card, now not allowed into US. Weird.
  • user avatar
    Reconstructing Visual Experiences from Brain Activity Evoked by Natural Movies. Rudimentary "Mind-reading". Very early, but breathtaking and presents so much potential. A great line of research steadily improving over decades. Paper: cell.com/current-biolog…
    GIF
  • user avatar
    The future is here... Machines taking over from humans.
    00:00
  • user avatar
    Naive Computer Vision model that hasn't been trained on both states of a glass door :)
    00:00
  • user avatar
    Climbing ever-greater slopes. I love this progression. By BEC.
    00:00
  • user avatar
    3D Face Reconstruction from a Single Image. Try your own face: cs.nott.ac.uk/~psxasj/3dme/ Code: github.com/AaronJackson/v…
    GIF
  • user avatar
    Creating super slow motion videos by predicting missing frames using a neural network, instead of simple interpolation. With code. Code: github.com/avinashpaliwal… Project: people.cs.umass.edu/~hzjiang/proje…
    00:00
  • user avatar
    Lyft open-sourced their autonomous driving dataset from its Level 5 self-driving fleet. - 55k human-labeled 3D frames - 7 cameras, 3 lidars - HD spatial semantic map: lanes, crosswalks, etc - Drivable surface map level5.lyft.com/dataset/
    00:00
  • user avatar
    Automated book scanning: automatically turning pages, dealing with page warps through surface tracking. Scanning 250 pages/minute. k2.t.u-tokyo.ac.jp/vision/BFS-Aut…
    00:00