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.
linear error modified standard backpropagation nonlinear error optimization criterion single hidden layer network
This is a preview of subscription content, log in to check access.
Abid, S., Fnaiech, F., Najim, M. 2001A fast feedforward training algorithm using a modified form of the standard backpropagation algorithmIEEE Transactions on Neural Networks12424430CrossRefGoogle Scholar
Asari, V.K. 2001Training of a feedforward multiple-valued neural networks by error backpropagation with a multilevel threshold functionIEEE Transactions on Neural Networks1215191521CrossRefGoogle Scholar
Bishop, C. 1995Neural Networks for Pattern RecognitionClarendonOxfordGoogle Scholar
Chowdhury, P.R., Singh, Y.P., Chansarkar, R.A. 1999Dynamic tunneling technique for efficient training of multilayer perceptronsIEEE. Transactions on Neural Networks104855Google Scholar
Hagan, M.T., Menhaj, M.B. 1994Training feedforward neural networks with the Marquardt algorithmIEEE Transactions on Neural Networks5989993CrossRefGoogle Scholar
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.Google Scholar
Kathirvalavakumar, T., Thangavel, P. 2003A new learning algorithm using simultaneous perturbation with weight initializationNeural Processing Letters175568CrossRefGoogle Scholar
Krogh, A., Hertz, J. 1992Generalization in a linear perceptron in the presence of noiseJournal of Physics A – Mathematical and General2511351147ADSMathSciNetGoogle Scholar
Kwok, T.Y., Yeung, D.Y. 1997Objective functions for training new hidden units in constructive neural networksIEEE Transactions on Neural Networks811311147Google Scholar
Lera, G., Pinzolas, M. 2002Neighborhood based Levenberg–Marquardt algorithm for neural network trainingIEEE Transactions on Neural Networks1312001203CrossRefGoogle Scholar
Parisi, R., DiClaudi, E.D., Orlandi, G., Rao, B.D. 1996A generalized learning paradigm exploiting the structure of feedforward neural networksIEEE Transactions on Neural Networks714501459CrossRefGoogle Scholar