Login / Signup
Neural networks are a priori biased towards Boolean functions with low entropy.
Chris Mingard
Joar Skalse
Guillermo Valle Pérez
David Martínez-Rubio
Vladimir Mikulik
Ard A. Louis
Published in:
CoRR (2019)
Keyphrases
</>
boolean functions
neural network
uniform distribution
relevant variables
prime implicants
threshold functions
dnf formulae
functional properties
multi valued
machine learning
membership queries
linear threshold
polynomial size
disjunctive normal form
inference rules