Meta-cognitive neural network for classification problems in a sequential learning framework

In 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 r...

Full description

Saved in:
Bibliographic Details
Main Authors: Sateesh Babu, Giduthuri, Suresh, Sundaram
Other Authors: School of Computer Engineering
Format: Article
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/98781
http://hdl.handle.net/10220/13658
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:In 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.