Computational limitations on learning from examples
Journal of the ACM (JACM)
An introduction to computational learning theory
An introduction to computational learning theory
A Linear-Time Algorithm for Finding Tree-Decompositions of Small Treewidth
SIAM Journal on Computing
Computers and Intractability: A Guide to the Theory of NP-Completeness
Computers and Intractability: A Guide to the Theory of NP-Completeness
Theoretical Computer Science - Selected papers in honour of Setsuo Arikawa
Parameterized Complexity Theory (Texts in Theoretical Computer Science. An EATCS Series)
Parameterized Complexity Theory (Texts in Theoretical Computer Science. An EATCS Series)
Learning a circuit by injecting values
Proceedings of the thirty-eighth annual ACM symposium on Theory of computing
Inferring social networks from outbreaks
ALT'10 Proceedings of the 21st international conference on Algorithmic learning theory
Hypothesizing about causal networks with positive and negative effects by meta-level abduction
ILP'10 Proceedings of the 20th international conference on Inductive logic programming
Completing causal networks by meta-level abduction
Machine Learning
Learning from interpretation transition
Machine Learning
Hi-index | 0.00 |
This paper studies problems of completing a given Boolean network (Boolean circuit) so that the input/output behavior is consistent with given examples, where we only consider acyclic networks. These problems arise in the study of inference of signaling networks using reporter proteins. We prove that these problems are NP-complete in general and a basic version remains NP-complete even for tree structured networks. On the other hand, we show that these problems can be solved in polynomial time for partial k-trees of bounded (constant) indegree if a logarithmic number of examples are given.