A meta-cognitive learning algorithm for a fully complex-valued relaxation network
This paper presents a meta-cognitive learning algorithm for a single hidden layer complex-valued neural network called “Meta-cognitive Fully Complex-valued Relaxation Network (McFCRN)”. McFCRN has two components: a cognitive component and a meta-cognitive component. A Fully Complex-valued Relaxation...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/97565 http://hdl.handle.net/10220/10621 |
| _version_ | 1811692937402122240 |
|---|---|
| author | Suresh, Sundaram Sundararajan, Narasimhan Savitha, R. |
| author2 | School of Computer Engineering |
| author_facet | School of Computer Engineering Suresh, Sundaram Sundararajan, Narasimhan Savitha, R. |
| author_sort | Suresh, Sundaram |
| collection | NTU |
| description | This paper presents a meta-cognitive learning algorithm for a single hidden layer complex-valued neural network called “Meta-cognitive Fully Complex-valued Relaxation Network (McFCRN)”. McFCRN has two components: a cognitive component and a meta-cognitive component. A Fully Complex-valued Relaxation Network (FCRN) with a fully complex-valued Gaussian like activation function (sechsech) in the hidden layer and an exponential activation function in the output layer forms the cognitive component. The meta-cognitive component contains a self-regulatory learning mechanism which controls the learning ability of FCRN by deciding what-to-learn, when-to-learn and how-to-learn from a sequence of training data. The input parameters of cognitive components are chosen randomly and the output parameters are estimated by minimizing a logarithmic error function. The problem of explicit minimization of magnitude and phase errors in the logarithmic error function is converted to system of linear equations and output parameters of FCRN are computed analytically. McFCRN starts with zero hidden neuron and builds the number of neurons required to approximate the target function. The meta-cognitive component selects the best learning strategy for FCRN to acquire the knowledge from training data and also adapts the learning strategies to implement best human learning components. Performance studies on a function approximation and real-valued classification problems show that proposed McFCRN performs better than the existing results reported in the literature. |
| first_indexed | 2024-10-01T06:43:43Z |
| format | Journal Article |
| id | ntu-10356/97565 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T06:43:43Z |
| publishDate | 2013 |
| record_format | dspace |
| spelling | ntu-10356/975652020-05-28T07:18:10Z A meta-cognitive learning algorithm for a fully complex-valued relaxation network Suresh, Sundaram Sundararajan, Narasimhan Savitha, R. School of Computer Engineering DRNTU::Engineering::Computer science and engineering This paper presents a meta-cognitive learning algorithm for a single hidden layer complex-valued neural network called “Meta-cognitive Fully Complex-valued Relaxation Network (McFCRN)”. McFCRN has two components: a cognitive component and a meta-cognitive component. A Fully Complex-valued Relaxation Network (FCRN) with a fully complex-valued Gaussian like activation function (sechsech) in the hidden layer and an exponential activation function in the output layer forms the cognitive component. The meta-cognitive component contains a self-regulatory learning mechanism which controls the learning ability of FCRN by deciding what-to-learn, when-to-learn and how-to-learn from a sequence of training data. The input parameters of cognitive components are chosen randomly and the output parameters are estimated by minimizing a logarithmic error function. The problem of explicit minimization of magnitude and phase errors in the logarithmic error function is converted to system of linear equations and output parameters of FCRN are computed analytically. McFCRN starts with zero hidden neuron and builds the number of neurons required to approximate the target function. The meta-cognitive component selects the best learning strategy for FCRN to acquire the knowledge from training data and also adapts the learning strategies to implement best human learning components. Performance studies on a function approximation and real-valued classification problems show that proposed McFCRN performs better than the existing results reported in the literature. 2013-06-25T04:51:26Z 2019-12-06T19:44:07Z 2013-06-25T04:51:26Z 2019-12-06T19:44:07Z 2012 2012 Journal Article Savitha, R., Suresh, S., & Sundararajan, N. (2012). A meta-cognitive learning algorithm for a fully complex-valued relaxation network. Neural networks, 32, 209-218. 0893-6080 https://hdl.handle.net/10356/97565 http://hdl.handle.net/10220/10621 10.1016/j.neunet.2012.02.015 en Neural networks © 2012 Elsevier Ltd. |
| spellingShingle | DRNTU::Engineering::Computer science and engineering Suresh, Sundaram Sundararajan, Narasimhan Savitha, R. A meta-cognitive learning algorithm for a fully complex-valued relaxation network |
| title | A meta-cognitive learning algorithm for a fully complex-valued relaxation network |
| title_full | A meta-cognitive learning algorithm for a fully complex-valued relaxation network |
| title_fullStr | A meta-cognitive learning algorithm for a fully complex-valued relaxation network |
| title_full_unstemmed | A meta-cognitive learning algorithm for a fully complex-valued relaxation network |
| title_short | A meta-cognitive learning algorithm for a fully complex-valued relaxation network |
| title_sort | meta cognitive learning algorithm for a fully complex valued relaxation network |
| topic | DRNTU::Engineering::Computer science and engineering |
| url | https://hdl.handle.net/10356/97565 http://hdl.handle.net/10220/10621 |
| work_keys_str_mv | AT sureshsundaram ametacognitivelearningalgorithmforafullycomplexvaluedrelaxationnetwork AT sundararajannarasimhan ametacognitivelearningalgorithmforafullycomplexvaluedrelaxationnetwork AT savithar ametacognitivelearningalgorithmforafullycomplexvaluedrelaxationnetwork AT sureshsundaram metacognitivelearningalgorithmforafullycomplexvaluedrelaxationnetwork AT sundararajannarasimhan metacognitivelearningalgorithmforafullycomplexvaluedrelaxationnetwork AT savithar metacognitivelearningalgorithmforafullycomplexvaluedrelaxationnetwork |