A general insight into the effect of neuron structure on classification

Knowledge and Information Systems

Volumn 30, Issue 1, 2012, Pages 135-154

  Yazdi, Hadi Sadoghi ^a   Rowhanimanesh, Alireza ^a   Modares, Hamidreza ^a  

^a FERDOWSI UNIVERSITY OF MASHHAD   (Iran)

Author keywords

Classification; Iris data classification; Multilayer perceptron (MLP); Neuron structure; Nonlinear input mapping; Nonmonotonic activation function

Indexed keywords

EID: 84855549012     PISSN: 02191377     EISSN: 02193116     Source Type: Journal    
DOI: 10.1007/s10115-011-0392-6     Document Type: Article

References (37)

1. Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New york.
2. Chandra P, Singh Y (2004) An activation function adapting training algorithm for sigmoidal feedforward networks. Neurocomputing 61: 429-437.
3. Daqia G, Genxinga Y (2003) Influences of variable scales and activation functions on the performances of multilayer feedforward neural networks. Pattern Recognit 36: 869-878.
4. Daqi G, Yan J (2005) Classification methodologies of multilayer perceptrons with sigmoid activation functions. Pattern Recognit 38: 1469-1482.
5. Durbin R, Rumelhart D (1989) Products units: a computationally powerful and biologically plausible extension to backpropagation networks. Neural Comput 1: 133-142.
6. Duch W, Janhowski N (1999) Survey of neural transfer functions. Neural Comput 2: 163-212.
7. Efe M (2008) Novel neuronal activation functions for feedforward neural networks. Neural Process Lett 8: 63-79.
8. Funahashi K (1998) Multilayer neural networks and Bayes decision theory. Neural Netw 11: 209-213.
9. Garfield S, Wermter S (2006) Call classification using recurrent neural networks, support vector machines and finite state automata. Knowl Inf Syst 9: 131-156.
10. Gibson GJ, Cowan CFN (1990) On the decision regions of multilayer perceptrons. In: Proceedings of IEEE 78(9): 1590-1594.
11. Guarnieri S, Piazza F, Uncini A (1999) Multilayer feedforward networks with adaptive spline activation function. IEEE Trans Neural Netw 10: 672-684.
12. Gutierrez PA, Hervas C, Carbonero M et al (2009) Combined projection and kernel basis functions for classification in evolutionary neural networks. Neurocomputing 72: 2731-2742.
13. Hagan MT, Demuth HB, Beale MH (1999) Neural network design. PWS Publishing Company, Boston.
14. Hara K, Nakayamma K (1994) Comparison of activation functions in multilayer neural network for pattern classification. In: IEEE world congress on computational intelligence, IEEE in conference on neural networks, pp 2997-3002.
15. Holland JH (1975) Adaptation in natural and artificial systems. The University of Michigan Press, Ann Arbor.
16. Homik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Netw 4: 251-257.
17. Homik K (1993) Some new results on neural network approximation. Neural Netw 6: 1069-1072.
18. Huang SC, Huang YF (1991) Bounds on the number of hidden neurons in multilayer perceptrons. IEEE Trans Neural Netw 2: 47-55.
19. Huang GB, Chen YQ, Babri HA (2000) Classification ability of single hidden layer feedforward neural networks. IEEE Trans Neural Netw 11: 799-801.
20. Karaköse M, Akin E (2004) Type-2 fuzzy activation function for multilayer feedforward neural networks. In: IEEE international conference on systems, man and cybernetics, pp 3762-3767.
21. Lapedes A, Farber R (1988) How neural nets work. In: Anderson D (eds) Neural information processing systems. American Institute of Physics, New York, pp 442-456.
22. Leshno M, Lin VY, Pinkus A et al (1993) Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Netw 6: 861-867.
23. Lin SW, Chen SC, Wu WJ et al (2009) Parameter determination and feature selection for back- propagation network by particle swarm optimization. Knowl Inf Syst 21: 249-266.
24. Liu Q, Wang J (2008) Two k-winners-take-all networks with discontinuous activation functions. Neural Netw 21: 406-413.
25. Lippmann RP (1989) Pattern classification using neural networks. IEEE Commun Mag 27: 47-64.
26. Menon A, Mehrotra K, Mohan CK et al (1996) Characterization of a class of sigmoid functions with applications to neural networks. Neural Netw 9: 819-835.
27. Pao YH, Takefuji Y (1992) Functional-link net computing: theory, system architecture, and functionalities. IEEE Comput 25: 76-79.
28. Park DC (2009) Multiresolution-based bilinear recurrent neural network. Knowl Inf Syst 19: 235-248.
29. Piazza F, Uncini A, Zenobi M (1993) Artificial neural networks with adaptive polynomial activation function. In: Proceeding of the IJCNN, Bejing, pp 343-349.
30. Reddy CK, Park JH (2010) Multi-resolution boosting for classification and regression problems. Knowl Inf Syst. doi: 10. 1007/s10115-010-0358-0.
31. Specht DF (1991) A general regression neural network. IEEE Trans Neural Netw 2: 568-576.
32. Singh Y, Chandra P (2003) A class +1 sigmoidal activation functions for FANNs. J Econ Dyn Control 28: 183-187.
33. Sopena JM, Romero E, Alquezar R (1999) Neural networks with periodic and monotonic activation functions: a comparative study in classification problems. In: International conference on artificial neural networks, pp. 323-328.
34. UCI Machine Learning Repository: Iris Data Set. http://archive. ics. uci. edu/ml/datasets/Iris.
35. Vecci L, Piazza F, Uncini A (1998) Learning and approximation capabilities of adaptive spline activation function neural networks. Neural Netw 1: 259-270.
36. Vaughn ML (1999) Derivation of the multilayer perceptron weight constraints for direct network interpretation and knowledge discovery. Neural Netw 12: 1259-1271.
37. Wu Y, Zhao M, Ding X (1997) Beyond weights adaptation: a new neuron model with trainable activation function and its supervised learning. In: International conference on neural networks, pp 1152-1157.