Abstract
This paper presents a parameter by parameter (PBP) algorithm for speeding up the training of multilayer perceptrons (MLP). This new algorithm uses an approach similar to that of the layer by layer (LBL) algorithm, taking into account the input errors of the output layer and hidden layer. The proposed PBP algorithm, however, is not burdened by the need to calculate the gradient of the error function. In each iteration step, the weights or thresholds can be optimized directly one by one with other variables fixed. Four classes of solution equations for parameters of networks are deducted. The effectiveness of the PBP algorithm is demonstrated using two benchmarks. In comparisons with the BP algorithm with momentum (BPM) and the conventional LBL algorithms, PBP obtains faster convergences and better simulation performances.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
Explore related subjects
Discover the latest articles and news from researchers in related subjects, suggested using machine learning.Abbreviations
- BPM:
-
BP algorithm with momentum
- LBL:
-
Layer by Layer
- MLP:
-
Multilayer Perceptrons
- MNN:
-
Modular Neural Network
- MSE:
-
Mean Square Error
- PBP:
-
Parameter by Parameter
References
D.E. Rumelhart G.E. Hinton R.J. Williams (1986) Learning internal representations by error backpropagation D.E. Rumelhart J.L. McClelland (Eds) Parallel Distributed Processing’s MIT press Cambridge, MA
R.A. Jacobs (1988) ArticleTitleIncreased rates of convergence through learning rate adaptation Neural Networks 1 295–307 Occurrence Handle10.1016/0893-6080(88)90003-2
H.B. Kim S.H. Jung T.G. Kim et al. (1996) ArticleTitleFast learning method for back-propagation neural network by evolutionary adaptation of learning rates Neurocomputing 11 101–106 Occurrence Handle10.1016/0925-2312(96)00009-4
S. Abid M. FnaiechF. 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
Y.H. Zweiri J.F. Whidborne L.D. Seneviratne (2003) ArticleTitleA three-term backpropagation algorithm Neurocomputing 50 305–318 Occurrence Handle10.1016/S0925-2312(02)00569-6
E. Barnard (1992) ArticleTitleOptimization for training neural nets IEEE Transactions on Neural Networks 3 232–240
M.T. Hagan M.B. Menhaj (1994) ArticleTitleTraining feedforward networks with the marquardt algorithm IEEE Transactions on Neural Networks 5 989–993 Occurrence Handle10.1109/72.329697
R. Parisi E.D. Claudio ParticleDi G. Orlandi (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
Y.F. Yam T.W.S. Chow (1995) ArticleTitleAccelerated training algorithm for feedforward neural networks based on least squares method Neural Processing Letters 2 20–25
F. Biegle-König F. Bärmann (1993) ArticleTitleA learning algorithm for multilayered neural networks based on linear least squares problems Neural Networks 6 127–131
S. Ergezinger E. Thomsen (1995) ArticleTitleAn accelerated learning algorithm for multilayer perceptrons: Optimization layer by layer IEEE Transactions on Neural Networks 6 31–42 Occurrence Handle10.1109/72.363452
G.-J. Wang C.-C. Chen (1996) ArticleTitleA fast multilayer neural networks training algorithm based on the layer-by-layer optimizing procedures IEEE Transactions on Neural Networks 7 768–775 Occurrence Handle10.1109/72.548174
S.-H. Oh S.-Y. Lee (1999) ArticleTitleA new error function at hidden layers for fast training of Multilayer perceptrons IEEE Transactions on Neural Networks 10 960–964
J.Y.F. Yam 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
G. Strang (1976) Linear Algebra and its Applications Academic Press New York
M.S. Bazaraa C.M. Shetty (1979) Nonlinear Programming Theory and Algorithms John Wiley & Sons Canada
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Li, Y., Zhang, D. & Wang, K. Parameter by Parameter Algorithm for Multilayer Perceptrons. Neural Process Lett 23, 229–242 (2006). https://doi.org/10.1007/s11063-006-0003-9
Issue Date:
DOI: https://doi.org/10.1007/s11063-006-0003-9