An equalized error backpropagation algorithm for the on-line training of multilayer perceptrons

IEEE Transactions on Neural Networks

Volumn 13, Issue 3, 2002, Pages 532-541

  Martens, Jean Pierre ^a   Weymaere, Nico ^a  

^a GHENT UNIVERSITY   (Belgium)

Author keywords

Error backpropagation (EBP); Multilayer perceptrons (MLPs); On line training; Pattern recognition

Indexed keywords

ALGORITHMS; BACKPROPAGATION; CONVERGENCE OF NUMERICAL METHODS; ERROR ANALYSIS; ONLINE SYSTEMS; PATTERN RECOGNITION;

ERROR BACKPROPAGATION (EBP);

MULTILAYER NEURAL NETWORKS;

EID: 0036565199     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/TNN.2002.1000122     Document Type: Article

References (21)

1. Links between Markov models and multilayer perceptrons
2. An adaptive training algorithm for backpropagation networks
3. A new criterion for posterior probability estimation with neural nets
4. Local training for radial basis function networks: Toward solving the hidden unit problem
5. Increased rates of convergence through learning rate adaptation
6. Phonetic classification using multi-layer perceptrons
7. A stochastically motivated random initialization of pattern classifying MLP's
8. A new dynamic programming/multi-layer perceptron hybrid for continuous speech recognition
9. Learning sets of filters using back-propagation
10. Accelerated learning in layered neural networks
11. Identification of ef-group 22 campylobacters from gastroenteritis cases as campylobacter concisus
12. A fast and robust learning algorithm for feedforward neural networks
13. On the initialization and the optimization of multi-layer perceptrons
14. Convergence conditions for ascent methods
15. A sequential learning approach for single hidden layer neural networks