Abstract
In this paper, a new efficient learning procedure for training single hidden layer feedforward network is proposed. This procedure trains the output layer and the hidden layer separately. A new optimization criterion for the hidden layer is proposed. Existing methods to find fictitious teacher signal for the output of each hidden neuron, modified standard backpropagation algorithm and the new optimization criterion are combined to train the feedforward neural networks. The effectiveness of the proposed procedure is shown by the simulation results.
Similar content being viewed by others
References
S. Abid F. Fnaiech M. Najim (2001) ArticleTitleA fast feedforward training algorithm using a modified form of the standard backpropagation algorithm IEEE Transactions on Neural Networks 12 424–430 Occurrence Handle10.1109/72.914537
V.K. Asari (2001) ArticleTitleTraining of a feedforward multiple-valued neural networks by error backpropagation with a multilevel threshold function IEEE Transactions on Neural Networks 12 1519–1521 Occurrence Handle10.1109/72.963789
C. Bishop (1995) Neural Networks for Pattern Recognition Clarendon Oxford
P.R. Chowdhury Y.P. Singh R.A. Chansarkar (1999) ArticleTitleDynamic tunneling technique for efficient training of multilayer perceptrons IEEE. Transactions on Neural Networks 10 48–55
M.T. Hagan M.B. Menhaj (1994) ArticleTitleTraining feedforward neural networks with the Marquardt algorithm IEEE Transactions on Neural Networks 5 989–993 Occurrence Handle10.1109/72.329697
Hinton, G. E.: Connectioniest Learning Procedure in Machine Learning: Paradigms and Methods, In: J. G. Carbonell, (ed.), pp. 185–234, Cambridge MA: MIT press 1989.
T. Kathirvalavakumar P. Thangavel (2003) ArticleTitleA new learning algorithm using simultaneous perturbation with weight initialization Neural Processing Letters 17 55–68 Occurrence Handle10.1023/A:1022919300793
A. Krogh J. Hertz (1992) ArticleTitleGeneralization in a linear perceptron in the presence of noise Journal of Physics A – Mathematical and General 25 1135–1147 Occurrence Handle1992JPhA...25.1135K Occurrence Handle92m:82104
T.Y. Kwok D.Y. Yeung (1997) ArticleTitleObjective functions for training new hidden units in constructive neural networks IEEE Transactions on Neural Networks 8 1131–1147
G. Lera M. Pinzolas (2002) ArticleTitleNeighborhood based Levenberg–Marquardt algorithm for neural network training IEEE Transactions on Neural Networks 13 1200–1203 Occurrence Handle10.1109/TNN.2002.1031951
R. Parisi E.D. DiClaudi G. Orlandi B.D. Rao (1996) ArticleTitleA generalized learning paradigm exploiting the structure of feedforward neural networks IEEE Transactions on Neural Networks 7 1450–1459 Occurrence Handle10.1109/72.548172
R.D. Reed R.J. Marks SuffixII (1999) Neural Smithing Supervised Learning in Feedforward Artificial Neural Networks MIT Cambridge
P. Thangavel T. Kathirvalavakumar (2002) ArticleTitleTraining feedforward networks using simultaneous perturbation with dynamic tunneling Neurocomputing 48 691–704 Occurrence Handle10.1016/S0925-2312(01)00639-7
P. Thangavel T. Kathirvalavakumar (2003) ArticleTitleSimultaneous perturbation for single hidden layer networks-cascade learning Neurocomputing 50 193–209 Occurrence Handle10.1016/S0925-2312(01)00704-4
Y. Yamamoto P.N. Nikiforuk (2000) ArticleTitleA new supervised learning algorithm for multilayered and interconnected neural networks IEEE Transactions on Neural Networks 11 36–46 Occurrence Handle10.1109/72.822508
J.Y.F. Yam T.W.S. Chow (1997) ArticleTitleExtended least squares based algorithm for training feedforward networks IEEE Transactions on Neural Networks 8 806–810 Occurrence Handle10.1109/72.572119
J.Y.F. Yam T.W.S. Chow (2000) ArticleTitleA weight initialization method for improving training speed in feedforward neural networks Neurocomputing 30 219–232 Occurrence Handle10.1016/S0925-2312(99)00127-7
J.Y.F. Yam T.W.S. Chow (2001) ArticleTitleFeedforward networks training speed enhancement by optimal initialization of the synaptic coefficients IEEE Transactions on Neural Networks 12 430–434 Occurrence Handle10.1109/72.914538
X. Yu M. Onder Efe O. Kaynak (2002) ArticleTitleA general backpropagation algorithm for feedforward neural networks learning IEEE Transactions on Neural Networks 13 251–259
Author information
Authors and Affiliations
Corresponding author
Additional information
*The work of P. Thangavel is partially supported by UGC, Government of India sponsored project.
Rights and permissions
About this article
Cite this article
Kathirvalavakumar, T., Thangavel, P. A Modified Backpropagation Training Algorithm for Feedforward Neural Networks*. Neural Process Lett 23, 111–119 (2006). https://doi.org/10.1007/s11063-005-3501-2
Issue Date:
DOI: https://doi.org/10.1007/s11063-005-3501-2