A weight initialization method for improving training speed in feedforward neural network
Top Cited Papers
- 31 January 2000
- journal article
- Published by Elsevier BV in Neurocomputing
- Vol. 30 (1-4), 219-232
- https://doi.org/10.1016/s0925-2312(99)00127-7
Abstract
No abstract availableKeywords
This publication has 15 references indexed in Scilit:
- A stochastically motivated random initialization of pattern classifying MLPsNeural Processing Letters, 1996
- Hierarchical neural networks for time-series analysis and controlNetwork: Computation in Neural Systems, 1994
- Training feedforward networks with the Marquardt algorithmIEEE Transactions on Neural Networks, 1994
- Initializing back propagation networks with prototypesNeural Networks, 1993
- A learning algorithm for multilayered neural networks based on linear least squares problemsNeural Networks, 1993
- Probabilistic Neural NetworksPublished by Elsevier BV ,1993
- New approach to selection of initial values of weights in neural function approximationElectronics Letters, 1993
- Statistically controlled activation weight initialization (SCAWI)IEEE Transactions on Neural Networks, 1992
- Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weightsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1990
- Fast learning in artificial neural systems: multilayer perceptron training using optimal estimationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1988