HN Explorer

MrUssek

↗ HN profile [ 97.6 ms ] full profile
Karma
203
Created
April 1, 2019 (7y ago)
Submissions
0
  1. China has trained a 10 trillion parameter language model (twitter.com)
    4 points 0
  2. What is your backup if the tech industry crashes?
    4 points 10
  3. The Future of Deep Learning Is Photonic (spectrum.ieee.org)
    1 points 0
  4. Separating MNIST digits using Optimal Transport (mrussek.com)
    1 points 0
  5. Enigma: GPT-2 trained on 10K Nature Papers: Can you spot the difference? (stefanzukin.com)
    183 points 105
  6. GShard: Scaling giant models with conditional computation and automatic sharding (arxiv.org)
    112 points 35