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
id sg-ntu-dr.10356-98781
record_format dspace
spelling sg-ntu-dr.10356-987812020-05-28T07:18:10Z Meta-cognitive neural network for classification problems in a sequential learning framework Sateesh Babu, Giduthuri Suresh, Sundaram School of Computer Engineering DRNTU::Engineering::Computer science and engineering 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. 2013-09-24T07:28:18Z 2019-12-06T19:59:36Z 2013-09-24T07:28:18Z 2019-12-06T19:59:36Z 2011 2011 Journal Article Sateesh Babu, G., & Suresh, S. (2011). Meta-cognitive neural network for classification problems in a sequential learning framework. Neurocomputing, 81, 86-96. https://hdl.handle.net/10356/98781 http://hdl.handle.net/10220/13658 10.1016/j.neucom.2011.12.001 en Neurocomputing
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering
spellingShingle DRNTU::Engineering::Computer science and engineering
Sateesh Babu, Giduthuri
Suresh, Sundaram
Meta-cognitive neural network for classification problems in a sequential learning framework
description 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.
author2 School of Computer Engineering
author_facet School of Computer Engineering
Sateesh Babu, Giduthuri
Suresh, Sundaram
format Article
author Sateesh Babu, Giduthuri
Suresh, Sundaram
author_sort Sateesh Babu, Giduthuri
title Meta-cognitive neural network for classification problems in a sequential learning framework
title_short Meta-cognitive neural network for classification problems in a sequential learning framework
title_full Meta-cognitive neural network for classification problems in a sequential learning framework
title_fullStr Meta-cognitive neural network for classification problems in a sequential learning framework
title_full_unstemmed Meta-cognitive neural network for classification problems in a sequential learning framework
title_sort meta-cognitive neural network for classification problems in a sequential learning framework
publishDate 2013
url https://hdl.handle.net/10356/98781
http://hdl.handle.net/10220/13658
_version_ 1681056537056903168