Results 1 to 10 of about 219,190 (262)

Comparative Analysis of Deterministic and Nondeterministic Decision Trees for Decision Tables from Closed Classes [PDF]

open access: yesEntropy, 2023
In this paper, we consider classes of decision tables with many-valued decisions closed under operations of the removal of columns, the changing of decisions, the permutation of columns, and the duplication of columns.
Azimkhon Ostonov, Mikhail Moshkov
doaj   +8 more sources

On Complexity of Deterministic and Nondeterministic Decision Trees for Conventional Decision Tables from Closed Classes

open access: yesEntropy, 2023
In this paper, we consider classes of conventional decision tables closed relative to the removal of attributes (columns) and changing decisions assigned to rows.
Azimkhon Ostonov, Mikhail Moshkov
doaj   +8 more sources

Complexity of Deterministic and Strongly Nondeterministic Decision Trees for Decision Tables From Closed Classes [PDF]

open access: yesIEEE Access, 2023
This paper investigates classes of decision tables (DTs) with 0-1-decisions that are closed under the removal of attributes (columns) and changes to the assigned decisions to rows.
Azimkhon Ostonov, Mikhail Moshkov
doaj   +4 more sources

Time and space complexity of deterministic and nondeterministic decision trees [PDF]

open access: yesAnnals of Mathematics and Artificial Intelligence, 2022
In this paper, we study arbitrary infinite binary information systems each of which consists of an infinite set called universe and an infinite set of two-valued functions (attributes) defined on the universe.
Mikhail Moshkov
exaly   +5 more sources

Efficient Modeling of Deterministic Decision Trees for Recognition of Realizable Decision Rules: Bounds on Weighted Depth

open access: yesAxioms
In this paper, an efficient algorithm for modeling the operation of a DDT (Deterministic Decision Tree) solving the problem of realizability of DRs (Decision Rules) is proposed and analyzed.
Kerven Durdymyradov, Mikhail Moshkov
doaj   +3 more sources

Approximating AC^0 by Small Height Decision Trees and a Deterministic Algorithm for #AC^0SAT [PDF]

open access: yes2012 IEEE 27th Conference on Computational Complexity, 2012
We show how to approximate any function in AC^0 by decision trees of much smaller height than its number of variables. More precisely, we show that any function in n variables computable by an unbounded fan-in circuit of AND, OR, and NOT gates that has size S and depth d can be approximated by a decision tree of height n - \beta n to within error exp(-\
Srikanth Srinivasan   +2 more
exaly   +3 more sources

Randomized versus Deterministic Decision Tree Size

open access: yesProceedings of the 55th Annual ACM Symposium on Theory of Computing, 2023
A classic result of Nisan [SICOMP ’91] states that the deterministic decision tree *depth* complexity of every total Boolean function is at most the cube of its randomized decision tree *depth* complexity.
A. Chattopadhyay   +4 more
semanticscholar   +5 more sources

End-to-end Learning of Deterministic Decision Trees [PDF]

open access: yesGerman Conference on Pattern Recognition, 2017
Conventional decision trees have a number of favorable properties, including interpretability, a small computational footprint and the ability to learn from little training data.
Thomas M. Hehn, F. Hamprecht
semanticscholar   +5 more sources

Proof complexity of systems of (non-deterministic) decision trees and branching programs [PDF]

open access: yesCoRR, 2019
This paper studies propositional proof systems in which lines are sequents of decision trees or branching programs - deterministic and nondeterministic.
S. Buss, Anupam Das, Alexander Knop
semanticscholar   +6 more sources

Deterministic and Stochastic Machine Learning Classification Models: A Comparative Study Applied to Companies’ Capital Structures

open access: yesMathematics
Corporate financing decisions, particularly the choice between equity and debt, significantly impact a company’s financial health and value. This study predicts binary corporate debt levels (high or low) using supervised machine learning (ML) models and ...
Joseph F. Hair   +3 more
doaj   +2 more sources

Home - About - Disclaimer - Privacy