Senior Research Fellow of School of Electrical & Electronic Engineering
Meta-cognition in Neural Networks
2013 International Joint Conference on Neural Networks
Dallas, Texas, USA,
August 4, 2013, 8:00am
School of Electrical and Electronics Engineering,
Nanyang Technological University, Singapore
School of Computer Engineering,
Nanyang Technological University, Singapore
This tutorial focuses on the recently developed neural network learning algorithms inspired from the models of human meta-cognition. Meta-cognition is defined as knowledge about knowledge. The model of human meta-cognition developed by Nelson and Narens  is the simplest model of meta-cognition available in the literature. This model is characterized by two components: a cognitive component that is the representation of knowledge, and a meta-cognitive component that enables measured acquisition of knowledge. To enable this measured acquisition, the meta-cognitive component has a dynamic model of the cognitive component, and continuously monitors and controls the learning ability of the cognitive component. In effect, meta-cognition involves continuous monitoring of the knowledge represented by the cognition, and using this understanding of knowledge representation to control the learning process actively.
We present the recently developed Meta-cognitive Radial Basis Function (McRBF) neural network that uses the concepts from the Nelson and Narens model of meta-cognition. McRBF also has a cognitive and a meta-cognitive component. An RBF neural network that is able to represent knowledge is the cognitive component, and a self-regulatory learning mechanism is its meta-cognitive component. For every sample instance in the training set, the self-regulatory learning mechanism compares the knowledge represented by the cognitive component and with that of the sample instance. Based on its judgment, it chooses suitable learning strategies, and decides what-to-learn, when-to-learn and how-to-learn in a meta-cognitive environment. We present the architecture and learning algorithm of McRBF [ 2]. As the McRBF self-regulates its own learning process, it has better generalization abilities. The decision making abilities of McRBF are demonstrated using standard benchmark classification problems and also with some real applications in the areas of recognizing human actions and medical informatics problems.
The meta-cognitive architecture has also been extended to the Complex domain and other neural network architectures like the extreme learning machines. The meta-cognitive fully complex-valued radial basis function and the meta-cognitive fully complex-valued relaxation networks are the two meta-cognitive architectures in the Complex domain. Also a fast learning algorithm using projection concepts for metacognitive learning will also be presented. In this tutorial we also discuss the architecture and learning algorithms of these networks along with their applications.
- A review on human learning from cognitive psychology
- Definitions of cognition/meta-cognition
- Meta-cognitive models in cognitive psychology
- Self-regulation in learning
- Meta-cognitive neural networks and its self-regulatory learning algorithms
· PBL-McRBFN classifier
- Benchmark evaluation and comparisons
- Applications in Medical informatics
· Alzheimer’s disease detection using MRI
· Parkinson’s disease detection using Gene/MRI
- Future directions
1. T. O. Nelson and L. Narens, Metacognition: Core Readings, ch. Metamemory: A theoritical framework and new findings, pp. 9- 24. Allyn and Bacon: Boston, T. O. nelson (ed.) ed., 1980.
2. R. Savitha, S. Suresh and N. Sundararajan, “Metacognitive Learning in a Fully Complex-Valued Radial Basis Function Neural Network,”, Neural Computation, vol. 24, no. 5, pp. 1297-1328, 2012.
3. G. Sateesh Babu, S. Suresh, Sequential projection based metacognitive learning in a Radial basis function network for classification problems, IEEE Trans, on Neural Networks and Learning Systems, 24(2), pp. 194-206, 2013.
4. G. Sateesh Babu, and S. Suresh, Meta-cognitive RBF networks and Its Projection based Learning Algorithm for Classification problems, Applied Soft Computing, 13(1), pp. 654-666, 2013.
5. G. Sateesh Babu, and S. Suresh, Parkinson’s Disease Prediction using Gene Expression – A Projection based Learning Metacognitive Neural Classifier Approach, Expert System with Applications, 40(5), pp. 1519-1529, 2012.
6. B. S. Mahanand, S. Suresh, N. Sundararajan and M. Aswatha Kumar, Identification of brain regions responsible for Alzheimer’s disease using a self-adaptive resource allocation network, Neural Networks, 32, pp. 313-322, 2012.