Performance improvement of backpropagation algorithm by automatic activation function gain tuning using fuzzy logic

Neurocomputing

Volumn 50, Issue , 2003, Pages 439-460

  Eom, Kihwan ^a   Jung, Kyungkwon ^a   Sirisena, Harsha ^b  

^a Dongguk University   (South Korea)

^b UNIVERSITY OF CANTERBURY   (New Zealand)

Author keywords

Activation function; Backpropagation; Fuzzy logic; Gain tuning; Neural network

Indexed keywords

ALGORITHMS; FUZZY SETS; HEURISTIC METHODS; PROBLEM SOLVING;

ACTIVATION FUNCTION GAIN;

BACKPROPAGATION;

ALGORITHM; ANALYTIC METHOD; ANALYTICAL PARAMETERS; ARTIFICIAL NEURAL NETWORK; AUTOMATION; CONTROLLED STUDY; MATHEMATICAL MODEL; PATTERN RECOGNITION; PRIORITY JOURNAL; REVIEW; SIMULATION;

EID: 0037239622     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0925-2312(02)00576-3     Document Type: Article

References (9)

1. C. Charalambous, Conjugate gradient algorithm for efficient training of artificial neural networks, IEE Proc. 139 (3) (1992) 301-310.
2. M.T. Hagan, H.B. Demuth, M. Beale, Neural Network Design, PWS Publishing, Boston, 1995.
3. M.T. Hagan, M. Menhaj, Training feedforward networks with the Marquardt algorithm, IEEE Trans. Neural Networks 5 (6) (1994) 187-199.
4. B. Hassibi, D.G. Stork, G.H. Wolff, Optimal brain surgeon and general network pruning, Proc. IEEE Int. Joint Conf. Neural Networks 2 (1992) 441-444.
5. P.G. Maghami, D.W. Sparks, Design of neural networks for fast convergence and accuracy: dynamics and control IEEE Trans. Neural Networks 11 (11) (2000) 113-123.
6. W. Pedrycz, Fuzzy Control and Fuzzy Systems, Wiley, New York, 1992.
7. I.P. Stoyanov, An improved backpropagation neural network learning, Proceedings of ICPR'96, 1996, pp. 586-588.
8. T.P. Vogl, J.K. Mangis, A.K. Zigler, W.T. Zink, D.L. Alkon, Accelerating the convergence of the backpropagation method, Biol. Cybernet. 59 (1988) 256-264.
9. J.M. Zurada, Introduction to Artificial Neural Systems, West Publishing Company, St. Paul, MN, 1992.