Results 11 to 20 of about 23,608 (225)
Evaluation of DNF Formulas [PDF]
, 2013 Stochastic Boolean Function Evaluation (SBFE) is the problem of determining the value of a given Boolean function $f$ on an unknown input $x$, when each bit of $x_i$ of $x$ can only be determined by paying a given associated cost $c_i$. Further, $x$ is drawn from a given product distribution: for each $x_i$, $Prob[x_i=1] = p_i$, and the bits are ...
Sarah R. Allen +3 more
+5 more sources
Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021 We introduce backdoor DNFs, as a tool to measure the theoretical hardness of CNF formulas. Like backdoor sets and backdoor trees, backdoor DNFs are defined relative to a tractable class of CNF formulas. Each conjunctive term of a backdoor DNF defines a partial assignment that moves the input CNF formula into the base class.
Sebastian Ordyniak +2 more
openalex +3 more sources
Proceedings of the Thirty-ThirdInternational Joint Conference on Artificial IntelligenceA classifier is considered interpretable if each of its decisions has an explanation which is small enough to be easily understood by a human user. A DNF can be seen as a binary classifier kappa over boolean domains. The size of an explanation of a positive decision taken by a DNF kappa is bounded by the size of the terms in kappa, since we can explain
Martin Cooper +2 more
+6 more sources
DNF are teachable in the average case [PDF]
Machine Learning, 2007 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Homin K. Lee +2 more
openalex +3 more sources
On learning visual concepts and DNF formulae [PDF]
Proceedings of the sixth annual conference on Computational learning theory - COLT '93, 1996 zbMATH Open Web Interface contents unavailable due to conflicting licenses.
Eyal Kushilevitz, Dan Roth
openalex +5 more sources
DNF sparsification beyond sunflowers [PDF]
Proceedings of the 51st Annual ACM SIGACT Symposium on Theory of Computing, 2019 There are two natural complexity measures associated with DNFs: their size, which is the number of clauses; and their width, which is the maximal number of variables in a clause. It is a folklore result that DNFs of small size can be approximated by DNFs of small width (logarithmic in the size). The other direction is much less clear. Gopalan, Meka and
Shachar Lovett, Jiapeng Zhang
openalex +3 more sources
Quantum DNF Learnability Revisited [PDF]
, 2002 We describe a quantum PAC learning algorithm for DNF formulae under the uniform distribution with a query complexity of $\tilde{O}(s^{3}/ + s^{2}/ ^{2})$, where $s$ is the size of DNF formula and $ $ is the PAC error accuracy. If $s$ and $1/ $ are comparable, this gives a modest improvement over a previously known classical query complexity of ...
Jeffrey C. Jackson +2 more
openalex +4 more sources
Hardness of learning DNFs using halfspaces [PDF]
Proceedings of the 53rd Annual ACM SIGACT Symposium on Theory of Computing, 2021 The problem of learning $t$-term DNF formulas (for $t = O(1)$) has been studied extensively in the PAC model since its introduction by Valiant (STOC 1984). A $t$-term DNF can be efficiently learnt using a $t$-term DNF only if $t = 1$ i.e., when it is an AND, while even weakly learning a $2$-term DNF using a constant term DNF was shown to be NP-hard by ...
Ghoshal, Suprovat, Saket, Rishi
openaire +2 more sources
Minimization of Boolean functions in the class of orthogonal disjunctive normal forms
Informatika, 2021 The orthogonal disjunctive normal forms (DNFs) of Boolean functions have wide applications in the logical design of discrete devices. The problem of DNF orthogonalization is to get for a given function such a DNF that any two its terms would be ...
Yu. V. Pottosin
doaj +1 more source
Learning DNF from random walks [PDF]
44th Annual IEEE Symposium on Foundations of Computer Science, 2003. Proceedings., 2004 We consider a model of learning Boolean functions from examples generated by a uniform random walk on {0,1}n. We give a polynomial time algorithm for learning decision trees and DNF formulas in this model. This is the first efficient algorithm for learning these classes in a natural passive learning model where the learner has no influence over the ...
Bshouty, Nader H. +3 more
openaire +1 more source