Almost optimal lower bounds for small depth circuits
STOC '86 Proceedings of the eighteenth annual ACM symposium on Theory of computing
The expressive power of voting polynomials
STOC '91 Proceedings of the twenty-third annual ACM symposium on Theory of computing
Constant depth circuits, Fourier transform, and learnability
Journal of the ACM (JACM)
On the computational power of depth-2 circuits with threshold and modulo gates
Theoretical Computer Science
Computing Boolean functions by polynomials and threshold circuits
Computational Complexity
Polynomial threshold functions, AC functions and spectrum norms
SFCS '90 Proceedings of the 31st Annual Symposium on Foundations of Computer Science
An efficient membership-query algorithm for learning DNF with respect to the uniform distribution
SFCS '94 Proceedings of the 35th Annual Symposium on Foundations of Computer Science
On data classification by iterative linear partitioning
Discrete Applied Mathematics - Discrete mathematics & data mining (DM & DM)
Toward Attribute Efficient Learning of Decision Lists and Parities
The Journal of Machine Learning Research
On data classification by iterative linear partitioning
Discrete Applied Mathematics
| Hi-index | 0.00 |
We study the computational power of decision lists over AND-functions versus threshold-驴 circuits. AND-decision lists are a natural generalization of formulas in disjunctive or conjunctive normal form. We show that, in contrast to CNF- and DNF-formulas, there are functions with small AND-decision lists which need exponential size unbounded weight threshold-驴 circuits. This implies that Jackson's polynomial learning algorithm for DNFs [7] which is based on the efficient simulation of DNFs by polynomial weight threshold-驴 circuits [8], cannot be applied to AND-decision lists. A further result is that for all k 驴 1 the complexity class defined by polynomial length ACk0-decision lists lies strictly between ACk+10 and ACk+20.