A self-organizing map-based initialization for hybrid training of feedforward neural networks
Authors:
- Mounir Ben NasrMNMounir Ben Nasr
- 31 December 2011
- journal article
- review article
- Published by Elsevier in Applied Soft Computing
- Vol. 11 (8) , 4458-4464
Abstract
No abstract availableKeywords
This publication has 37 references indexed in Scilit:
- Variable step search algorithm for feedforward networksNeurocomputing, 2008
- Growing Hierarchical Tree SOM: An unsupervised neural network with dynamic topologyNeural Networks, 2006
- Convergence of Gradient Method With Momentum for Two-Layer Feedforward Neural NetworksIEEE Transactions on Neural Networks, 2006
- A three-term backpropagation algorithmNeurocomputing, 2003
- Parallel growing and training of neural networks using output parallelismIEEE Transactions on Neural Networks, 2002
- A new pruning heuristic based on variance analysis of sensitivity informationIEEE Transactions on Neural Networks, 2001
- A fast feedforward training algorithm using a modified form of the standard backpropagation algorithmIEEE Transactions on Neural Networks, 2001
- A new evolutionary system for evolving artificial neural networksIEEE Transactions on Neural Networks, 1997
- Pruning algorithms-a surveyIEEE Transactions on Neural Networks, 1993
- Dynamic Node Creation in Backpropagation NetworksConnection Science, 1989