dc.contributor.authorSateesh Babu, Giduthuri
dc.contributor.authorSuresh, Sundaram
dc.identifier.citationSateesh Babu, G., & Suresh, S. (2011). Meta-cognitive neural network for classification problems in a sequential learning framework. Neurocomputing, 81, 86-96.
dc.description.abstractIn this paper, we propose a sequential learning algorithm for a neural network classifier based on human meta-cognitive learning principles. The network, referred to as Meta-cognitive Neural Network (McNN). McNN has two components, namely the cognitive component and the meta-cognitive component. A radial basis function network is the fundamental building block of the cognitive component. The meta-cognitive component controls the learning process in the cognitive component by deciding what-to-learn, when-to-learn and how-to-learn. When a sample is presented at the cognitive component of McNN, the meta-cognitive component chooses the best learning strategy for the sample using estimated class label, maximum hinge error, confidence of classifier and class-wise significance. Also sample overlapping conditions are considered in growth strategy for proper initialization of new hidden neurons. The performance of McNN classifier is evaluated using a set of benchmark classification problems from the UCI machine learning repository and two practical problems, viz., the acoustic emission for signal classification and a mammogram data set for cancer classification. The statistical comparison clearly indicates the superior performance of McNN over reported results in the literature.en_US
dc.subjectDRNTU::Engineering::Computer science and engineering
dc.titleMeta-cognitive neural network for classification problems in a sequential learning frameworken_US
dc.typeJournal Article
dc.contributor.schoolSchool of Computer Engineeringen_US

Files in this item


There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record