Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Sample Complexity of Scientific Discovery: PAC Learnability of Compositional Function Trees
Şuayp Talha Kocabay, Talha Rüzgar Akkuş, Kerem Yalçın
Scientific discovery via symbolic regression is often viewed as statistically and computationally intractable because the hypothesis space of expressions grows combinatorially with…
cs.LG2026
Selectivity and Shape in the Design of Forward-Forward Goodness Functions
Talha Ruzgar Akkus, Suayp Talha Kocabay, Kamer Ali Yuksel +1
The Forward-Forward (FF) algorithm trains networks layer-by-layer using a local "goodness function," yet the choice of activity statistic remains an important design question. We s…