Title
Exact Identification of the Structure of a Probabilistic Boolean Network from Samples.
Abstract
We study the number of samples required to uniquely determine the structure of a probabilistic Boolean network PBN, where PBNs are probabilistic extensions of Boolean networks. We show via theoretical analysis and computational analysis that the structure of a PBN can be exactly identified with high probability from a relatively small number of samples for interesting classes of PBNs of bounded indegree. On the other hand, we also show that there exist classes of PBNs for which it is impossible to uniquely determine the structure of a PBN from samples.
Year
DOI
Venue
2016
10.1109/TCBB.2015.2505310
IEEE/ACM Trans. Comput. Biology Bioinform.
Keywords
Field
DocType
Boolean functions,Probabilistic logic,Biological system modeling,Bioinformatics,Complexity theory,Mathematical model,Probability distribution
Small number,Boolean network,Boolean function,Computer science,Probability distribution,Artificial intelligence,Probabilistic logic,Bioinformatics,Sample complexity,Computational analysis,Machine learning,Bounded function
Journal
Volume
Issue
ISSN
13
6
1545-5963
Citations 
PageRank 
References 
1
0.35
0
Authors
5
Name
Order
Citations
PageRank
Xiaoqing Cheng1123.26
Tomoya Mori262.51
Yushan Qiu3206.28
Wai-Ki Ching468378.66
Tatsuya Akutsu52169216.05