alt Hacker NewsIIRC training starts with the initial state and the end state, and the end state is always oriented the same way. It would be interesting to see what would happen if the end state was rotated randomly though I suspect it wouldn't work so well.
IIRC training starts with the initial state and the end state, and the end state is always oriented the same way. It would be interesting to see what would happen if the end state was rotated randomly though I suspect it wouldn't work so well.
Checkout the Isotropic NCA blog from the Google Zurich team: https://google-research.github.io/self-organising-systems/is...