Pith. sign in

Note that we do not study k-sparse functions in the main text

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2025 1

verdicts

CONDITIONAL 1

roles

background 1

polarities

unclear 1

representative citing papers

Characterising the Inductive Biases of Neural Networks on Boolean Data

cs.LG · 2025-05-29 · conditional · novelty 6.0

Randomly initialized depth-2 discrete networks are a priori biased toward Boolean functions with small disjunctive normal form complexity, and this bias quantitatively predicts training and generalization behavior including weight-decay effects.

citing papers explorer

Showing 1 of 1 citing paper.

  • Characterising the Inductive Biases of Neural Networks on Boolean Data cs.LG · 2025-05-29 · conditional · none · ref 3

    Randomly initialized depth-2 discrete networks are a priori biased toward Boolean functions with small disjunctive normal form complexity, and this bias quantitatively predicts training and generalization behavior including weight-decay effects.