Title
Discovering the Relationship Between Generalization and Uncertainty by Incorporating Complexity of Classification.
Abstract
The generalization ability of a classifier learned from a training set is usually dependent on the classifier's uncertainty, which is often described by the fuzziness of the classifier's outputs on the training set. Since the exact dependency relation between generalization and uncertainty of a classifier is quite complicated, it is difficult to clearly or explicitly express this relation in gener...
Year
DOI
Venue
2018
10.1109/TCYB.2017.2653223
IEEE Transactions on Cybernetics
Keywords
Field
DocType
Training,Uncertainty,Mathematical model,Complexity theory,Cognition,Algorithm design and analysis,Indexes
Dependency relation,Algorithm design,Sensitivity analysis,Uncertainty analysis,Artificial intelligence,Problem complexity,Cognition,Statistical classification,Classifier (linguistics),Machine learning,Mathematics
Journal
Volume
Issue
ISSN
48
2
2168-2267
Citations 
PageRank 
References 
33
0.69
36
Authors
3
Name
Order
Citations
PageRank
Xizhao Wang13593166.16
Ran Wang243924.42
Chen Xu311215.26