Hacker News new | ask | show | jobs
by barking_biscuit 1212 days ago
>Because of randomization in initialization and training

Randomization in initialization seems like a pragmatic thing to do from a 'make the math work' perspective, but a really counter-intuitive thing to do when comparing the training process of our own wetware substrate. I know it's not a fair comparison, but just an interesting thought to me.