Comparison of new activation functions in neural network for forecasting financial time series

Neural Computing and Applications

Volumn 20, Issue 3, 2011, Pages 417-439

  da S Gomes, Gecynalda S ^a   Ludermir, Teresa B ^a   Lima, Leyla M M R ^a  

^a FEDERAL UNIVERSITY OF PERNAMBUCO   (Brazil)

Author keywords

Activation functions; CGF algorithm; Complementary log log; LM algorithm; Log log; Neural networks; Probit

Indexed keywords

ACTIVATION FUNCTIONS; CGF ALGORITHM; COMPLEMENTARY LOG-LOG; LM ALGORITHM; LOG-LOG; PROBIT;

BACKPROPAGATION ALGORITHMS; CONJUGATE GRADIENT METHOD; CONVERGENCE OF NUMERICAL METHODS; FINANCIAL DATA PROCESSING; FUNCTION EVALUATION; HYPERBOLIC FUNCTIONS; LAGRANGE MULTIPLIERS; LEARNING ALGORITHMS; NEURAL NETWORKS; TIME SERIES;

RADIOACTIVITY LOGGING;

EID: 79952817023     PISSN: 09410643     EISSN: None     Source Type: Journal    
DOI: 10.1007/s00521-010-0407-3     Document Type: Article

References (36)

1. Box GEP, Jenkins GM (1976) Time series analysis, forecasting and control. Holden Day, San Francisco.
2. Engle RF (1982) Autoregressive conditional heteroscedasticity with estimates of the variance of UK inflation. Econometrica 50: 987-1008.
3. Cybenko G (1989) Approximation by superpositions of a sigmoidal function. Math Control Signals Syst 2: 303-314.
4. White H (1990) Connectionist nonparametric regression: multilayer feedforward networks can learn arbitrary mappings. Neural Net 3: 535-550.
5. Gallant AR, White H (1992) On learning the derivatives of an unknown mapping with multilayer feedforward networks. Neural Net 5: 129-138.
6. Huang W, Lai K, Nakamori Y, Wang S, Yu L (2007) Neural networks in finance and economics forecasting. Int J Inf Technol Decision Making 6(1): 113-140.
7. Bollerslev T (1990) Modeling the coherence in short-run nominal exchange rates: a multivariate generalized arch model. Rev Econ Statist 72: 498-505.
8. Chandra P, Singh Y (2004) An activation function adapting training algorithm for sigmoidal feedforward networks. Neurocomputing 61: 429-437.
9. Duch W, Jankowski N (1999) Survey of neural transfer functions. Neural Comput Appl 2: 163-212.
10. Duch W, Jankowski N (2001) Transfer functions: hidden possibilities for better neural networks. In 9th European symposium on artificial neural networks, pp 81-94.
11. Singh Y and Chandra P (2003) A class +1 sigmoidal activation functions for FFANNs. J Econ Dynamic Control 28(1): 183-187.
12. Pao YH (1989) Adaptive pattern recognition and neural networks, 2nd edn. Addison-Wesley, New York.
13. Hartman E, Keeler JD, Kowalski JM (1990) Layered neural networks with gaussian hidden units as universal approximations. Neural Comput Appl 2(2): 210-215.
14. Hornik K (1991) Approximation capabilities of multilayer feedforward networks. Neural Net 4(2): 251-257.
15. Hornik K (1993) Some new results on neural network approximation. Neural Net 6(9): 1069-1072.
16. Leshno M, Lin VY, Pinkus A, Schocken S (1993) Multilayer feedforward networks with a nonpolynomial activation function can approximate any function. Neural Net 6(6): 861-867.
17. Leung H, Haykin S (1993) Rational function neural network. Neural Comput Appl 5(6): 928-938.
18. Giraud B, Lapedes A, Lon C, Lemm J (1995) Lorentzian neural nets. Neural Net 8(5): 757-767.
19. Skoundrianos EN, Tzafestas SG (2004) Modelling and FDI of dynamic discrete time systems using a MLP with a new sigmoidal activation function. J Intell Robotics Syst 41(1): 19-36.
20. Ma L, Khorasani K (2005) Constructive feedforward neural networks using hermite polynomial activation functions. IEEE Trans Neural Net 16(4): 821-833.
21. Wen C, Ma X (2005) A max-piecewise-linear neural network for function approximation. Neurocomputing 71: 843-852.
22. Efe MO (2008) Novel neuronal activation functions for feedforward neural networks. Neural Process Lett 28: 63-79.
23. Gomes GSS, Ludermir TB (2008) Complementary log-log and probit: activation functions implemented in artificial neural networks. In: 8th International conference on hybrid intelligent systems. IEEE Computer Society, pp 939-942.
24. Fletcher R, Reeves CM (1964) Function minimization by conjugate gradients. Comput J 7: 149-154.
25. Hagan MT, Demuth HB, Beale MH (1996) Neural network design. PWS Publishing, Boston.
26. Hagan MT, Menhaj M (1994) Training feed-forward networks with the marquardt algorithm. IEEE Trans Neural Net 5(6): 989-993.
27. Marquardt D (1963) An algorithm for least-squares estimation of nonlinear parameters. SIAM J Appl Math 11: 431-441.
28. Cybenko G (1988) Continuous valued neural networks with two hidden layers are sufficient technical report, Department of Computer Science, Tufts University, Medford, MA.
29. Hara K, Nakayamma K (1994) Comparison of activation functions in multilayer neural network for pattern classification. In: International conference on neural networks vol 5, IEEE World Congress on computational intelligence, pp 2997-3002.
30. Nelder JA, Wedderburn WM (1972) Generalized linear models. J Royal Statist Soc 3: 370-384.
31. McCullagh P, Nelder JA (1989) Generalized linear models, 2nd edn. Chapman and Hall, London.
32. Bliss CI (1935) The calculation of the dosage-mortality curve. Ann Appl Biol 22: 134-167.
33. Collett D (1994) Modelling survival data in medical research. Chapman and Hall, London.
34. Dobson AJ (2002) An introduction to generalized linear models, 2nd edn. Chapman and Hall, New York.
35. McCullagh P, Nelder JA (1989) Generalized linear models, 2nd ed. Chapman and Hall, London.
36. Haykin S (2001) Neural networks: a comprehensive foundation, 2nd edn. Prentice Hall, New Jersey.