steffen/self-replicating-neural-networks
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Added distinction time-as-fixpoint and time-to-vergence to be tracked.

Browse Source
This commit is contained in:
Maximilian Zorn
2021-05-22 14:43:20 +02:00
parent e9f6620b60
commit b1dc574f5b
2 changed files with 19 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
README.md
View File

@@ -13,6 +13,8 @@
- see `journal_robustness.py` for robustness test modeled after cristians robustness-exp (with the exeption that we put noise on the weights). Has `synthetic` bool to switch to hand-modeled perfect fixpoint instead of naturally trained ones.
- Also added two difference between the "time-as-fixpoint" and "time-to-verge" (i.e. to divergence / zero).
- We might need to consult about the "average loss per application step", as I think application loss get gradually higher the worse the weights get. So the average might not tell us much here.
- [ ] Adjust Self Training so that it favors second order fixpoints-> Second order test implementation (?)