The measure to describe the inexactness of approximation classifications is called the quality of approximation of X by B. It expresses the percentage of objects that can be correctly classified into class X, employing the attribute B (Pawlak 1982; Cheng et al. 2010): {gamma}_B(A)=frac{{displaystyle sum cardunderline{B}left({X}_iright)}}{card(U } (9).
This paper presents a new evolutionary cooperative learning scheme, able to solve function approximation and classification problems with improved accuracy and generalization capabilities.
The quality of approximation of classification, γ B (F), with respect to attributes B, expresses the ratio of all objects covered by the lower approximation R̲ B (F) = { R̲ B (Y1), R̲ B (Y2),…, R̲ B (Y n )} over all objects in U.
They validate the possibility of using these approximations for classification of sequences by UPGMA and NJ methods.
"Approximation Algorithms for Classification Problems with Pairwise Relationships: Metric Labeling and Markov Random Fields". Proc.
Approximation Algorithms for Classification Problems with Pairwise Relationships: Metric Labeling and Markov Random Fields.
The radial basis function (RBF) neural network is widely applied to the function approximation and pattern classification.
Active research topics include: multi-terminal and network information theory, compression, coding, capacity regions and bounds, novel security paradigms, privacy, statistical inference, classification, approximation approaches, energy-vs-performance tradeoffs, and dynamics of information flow.
Artificial neural networks (ANNs) have been applied to a wide variety of different areas such as prediction, approximation, modeling and classification.
Moreover, accurate estimation and classification of gene expression profiles are in need of reasonable approximation of the assumed covariance model to the truth.
