A meta-cognitive learning algorithm for a Fully Complex-valued Relaxation Network

Neural Networks

Volumn 32, Issue , 2012, Pages 209-218

  Savitha, R ^a   Suresh, S ^a   Sundararajan, N ^b  

^a NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

^b SRI JAYACHAMARAJENDRA COLLEGE OF ENGINEERING   (India)

Author keywords

Complex valued neural networks; Fully complex valued relaxation network; Meta cognition; Multi category classification; Self regulated learning mechanism

Indexed keywords

ACTIVATION FUNCTIONS; COGNITIVE COMPONENTS; COMPLEX-VALUED NEURAL NETWORKS; ERROR FUNCTION; FUNCTION APPROXIMATION; GAUSSIANS; HIDDEN LAYERS; HIDDEN NEURONS; HUMAN LEARNING; INPUT PARAMETER; LEARNING ABILITIES; LEARNING MECHANISM; LEARNING STRATEGY; META-COGNITION; METACOGNITIVES; MULTI-CATEGORY CLASSIFICATION; OUTPUT LAYER; OUTPUT PARAMETERS; PERFORMANCE STUDY; PHASE ERROR; SELF-REGULATED LEARNING; SYSTEM OF LINEAR EQUATIONS; TARGET FUNCTIONS; TRAINING DATA; TWO-COMPONENT;

LEARNING ALGORITHMS;

COGNITIVE SYSTEMS;

ACCURACY; ANALYTICAL ERROR; ARTICLE; ARTIFICIAL NEURAL NETWORK; CLASSIFICATION ALGORITHM; COGNITION; CONTROLLED STUDY; INTERMETHOD COMPARISON; KERNEL METHOD; LEARNING ALGORITHM; LEARNING STYLE; LINEAR SYSTEM; MATHEMATICAL COMPUTING; MATHEMATICAL MODEL; META COGNITIVE FULLY COMPLEX VALUED RELAXATION NETWORK; PRIORITY JOURNAL; QUALITY CONTROL; RADIAL BASED FUNCTION;

ALGORITHMS; ARTIFICIAL INTELLIGENCE; BENCHMARKING; CLASSIFICATION; COGNITION; FEMALE; HUMANS; IMAGE PROCESSING, COMPUTER-ASSISTED; LINEAR MODELS; MAMMOGRAPHY; NEURAL NETWORKS (COMPUTER); NORMAL DISTRIBUTION; SOFTWARE; SUPPORT VECTOR MACHINES;

EID: 84861781199     PISSN: 08936080     EISSN: 18792782     Source Type: Journal    
DOI: 10.1016/j.neunet.2012.02.015     Document Type: Article

References (38)

1. Aize, C., Song, Q., Yang, X., Liu, S., & Guo, C. (2004). Mammographic mass detection by vicinal support vector machine. In Proc. of ICNN'04, international conference on neural networks. Vol. 3 (pp. 1953-1958).
2. Aizenberg I., Moraga C. Multilayer feedforward neural network based on multi-valued neurons (MLMVN) and a backpropagation learning algorithm. Soft Computing 2007, 11(2):169-183.
3. Amin M.F., Murase K. Single-layered complex-valued neural network for real-valued classification problems. Neurocomputing 2009, 72(4-6):945-955.
4. Babu G.S., Suresh S. Meta-cognitive neural network for classification problems in a sequential learning framework. Neurocomputing 2012, (12):2621-2638. 10.1016/j.neucom.201112.001.
5. Blake, C., & Merz, C. (1998). UCI repository of machine learning databases. Department of Information and Computer Sciences. University of California, Irvine [URL: ]. http://archive.ics.uci.edu/ml/.
6. Chen S., McLaughlin S., Mulgrew B. Complex valued radial basis function network, part I: network architecture and learning algorithms. EURASIP Signal Processing Journal 1994, 35(1):19-31.
7. Deng J.P., Sundararajan N., Saratchandran P. Communication channel equalization using complex-valued minimal radial basis function neural networks. IEEE Transactions on Neural Networks 2002, 13(3):687-696.
8. Gamigami P. Atlas of mammography: new early signs in breast cancer 1996, Blackwell Science, Cambridge, MA, USA.
9. Haykin S. Neural networks: a comprehensive foundation 1998, Prentice Hall, New Jersey, USA.
10. Isaacson R., Fujita F. Metacognitive knowledge monitoring and self-regulated learning: academic success and reflections on learning. Journal of the Scholarship of Teaching and Learning 2006, 6(1):39-55.
11. Jianping D., Sundararajan N., Saratchandran P. Complex-valued minimal resource allocation network for nonlinear signal processing. International Journal of Neural Systems 2000, 10(2):95-106.
12. Kim T., Adali T. Fully complex multi-layer perceptron network for nonlinear signal processing. Journal of VLSI Signal Processing 2002, 32(1-2):29-43.
13. Li M.B., Huang G.-B., Saratchandran P., Sundararajan N. Fully complex extreme learning machine. Neurocomputing 2005, 68(1-4):306-314.
14. Li M.B., Huang G.B., Saratchandran P., Sundararajan N. Complex-valued growing and pruning RBF neural networks for communication channel equalisation. IEEE Proceedings-Vision, Image and Signal Processing 2006, 153(4):411-418.
15. Nelson T.O., Narens L. Metamemory: a theoritical framework and new findings. Metacognition: core readings 1980, 9-24. Allyn and Bacon, Boston, (Chapter). T.O. Nelson (Ed.).
16. Nitta T. The computational power of complex-valued neuron. Lecture notes in computer science 2003, Vol. 2714:993-1000.
17. Nitta T. Orthogonality of decision boundaries of complex-valued neural networks. Neural Computation 2004, 16(1):73-97.
18. Remmert R. Theory of complex functions 1991, Springer Verlag, New York, USA.
19. Rivers W.P. Autonomy at all costs: an ethnography of meta-cognitive self-assessment and self-management among experienced language learners. The Modern Language Journal 2001, 85(2):279-290.
20. Savitha R., Suresh S., Sundararajan N. A fully complex-valued radial basis function network and its learning algorithm. International Journal of Neural Systems 2009, 19(4):253-267.
21. Savitha, R., Suresh, S., & Sundararajan, N. (2010). A self-regulated learning in fully complex-valued radial basis function networks. In IEEE international joint conference on neural networks, 2010, IJCNN 2010 (pp. 1-8).
22. Savitha, R., Suresh, S., & Sundararajan, N. (2011). A fast learning complex-valued neural classifier for real-valued classification problems. In International joint conference on neural networks. IJCNN 2011 (pp. 2243-2249).
23. Savitha, R., Suresh, S., & Sundararajan, N. (2011). Meta-cognitive learning in fully complex-valued radial basis function network. Neural Computation, in press (). doi:10.1162/NECO_a_00254.
24. Savitha R., Suresh S., Sundararajan N. Fast learning circular complex-valued extreme learning machine (CC-ELM) for real-valued classification problems. Information Sciences 2012, 187(1):277-290.
25. Savitha R., Suresh S., Sundararajan N., Kim H.J. A fully complex-valued radial basis function classifier for real-valued classification. Neurocomputing 2011, 78(1):104-110.
26. Savitha R., Suresh S., Sundararajan N., Kim H.J. Fast learning fully complex-valued classifiers for real-valued classification problems. Lecture Notes in Computer Science (LNCS) 2011, Vol. 6675:602-609. ISNN 2011 (Part I). D. Liu (Ed.).
27. Savitha R., Suresh S., Sundararajan N., Saratchandran P. A new learning algorithm with logarithmic performance index for complex-valued neural networks. Neurocomputing 2009, 72(16-18):3771-3781.
28. Subashini T.S., Ramalingam V., Palanivel S. Automated assessment of breast tissue density in digital mammograms. Computer Vision and Image Understanding 2010, 114(1):33-43.
29. Suckling J., et al. The mammographic image analysis society digital mammogram database. Excerpta Medica International Congress Series 1994, 1069:375-378.
30. Suresh S., Dong K., Kim H.J. A sequential learning algorithm for self-adaptive resource allocation network classifier. Neurocomputing 2010, 73(16-18):3012-3019.
31. Suresh, S., Savitha, R., & Sundararajan, N. (2011). A fast learning fully complex-valued relaxation network (FCRN). In IEEE international joint conference on neural networks, 2011. IJCNN 2011 (pp. 1372-1377).
32. Suresh S., Savitha R., Sundararajan N. A sequential learning algorithm for complex-valued self-regulating resource allocation network-CSRAN. IEEE Transactions on Neural Networks 2011, 22(7):1061-1072.
33. Suresh, S., & Subramanian, K. (2011). A sequential learning algorithm for meta-cognitive neuro-fuzzy inference system for classification problems. In IEEE international joint conference on neural networks, 2011, IJCNN 2011 (pp.2507-2512).
34. Suresh S., Sundararajan N., Saratchandran P. Risk-sensitive loss functions for sparse multi-category classification problems. Information Sciences 2008, 178(12):2621-2638.
35. Wenden A.L. Meta-cognitive knowledge and language learning. Applied Linguistics 1998, 19(4):515-537.
36. Wirtinger W. Zur formalen theorie der funktionen von mehr komplexen veränderlichen. Annals of Mathematics 1927, 97:357-375.
37. Yu S.-S., Tsai W.-H. Relaxation by the Hopfield neural network. Pattern Recognition 1992, 25(2):197-209.
38. Zhang T. Statistical behavior and consistency of classification methods based on convex risk minimization. Annals of Statistics 2003, 32(1):56-85.