Using Unlabelled Data to Train a Multilayer Perceptron

Authors:
Antanas Verikas;Adas Gelzinis;Kerstin Malmqvist
Affiliations:
Intelligent Systems Laboratory, Halmstad University, S-301 18 Halmstad, Sweden;Kaunas University of Technology, 3031, Kaunas, Lithuania;Intelligent Systems Laboratory, Halmstad University, S-301 18 Halmstad, Sweden
Venue:
Neural Processing Letters
Year:
2001

Citing 14
Cited 5

Bayesian interpolation

Neural Computation
Fuzzy sets and fuzzy logic: theory and applications

Fuzzy sets and fuzzy logic: theory and applications
On the exponential value of labeled samples

Pattern Recognition Letters
Face recognition using a hybrid supervised/unsupervised neural network

Pattern Recognition Letters
Colour image segmentation by modular neural network

Pattern Recognition Letters
Time-series segmentation using predictive modular neural networks

Neural Computation
Backpropagation learning algorithms for classification with fuzzy mean square error

Pattern Recognition Letters
Combined learning and use for a mixture model equivalent to the RBF classifier

Neural Computation
Incorporating test inputs into learning

NIPS '97 Proceedings of the 1997 conference on Advances in neural information processing systems 10
Probabilistic modeling for face orientation discrimination: learning from labeled and unlabeled data

Proceedings of the 1998 conference on Advances in neural information processing systems II
Using labelled and unlabeled data to train a multilayer perceptron for color classification in graphic arts

IEA/AIE '99 Proceedings of the 12th international conference on Industrial and engineering applications of artificial intelligence and expert systems: multiple approaches to intelligent systems
Training Algorithm with Incomplete Data for Feed-ForwardNeural Networks

Neural Processing Letters
Neural Networks for Pattern Recognition

Neural Networks for Pattern Recognition
Partially supervised clustering for image segmentation

Pattern Recognition

Intelligent vocal cord image analysis for categorizing laryngeal diseases

IEA/AIE'2005 Proceedings of the 18th international conference on Innovations in Applied Artificial Intelligence
Semi-supervised learning with multilayer perceptron for detecting changes of remote sensing images

PReMI'07 Proceedings of the 2nd international conference on Pattern recognition and machine intelligence
Change Detection of Remote Sensing Images with Semi-supervised Multilayer Perceptron

Fundamenta Informaticae
Pattern classification and clustering: A review of partially supervised learning approaches

Pattern Recognition Letters
Semi-supervised change detection using modified self-organizing feature map neural network

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

This Letter presents an approach to using both labelled and unlabelled data to train a multilayer perceptron. The unlabelled data are iteratively pre-processed by a perceptron being trained to obtain the soft class label estimates. It is demonstrated that substantial gains in classification performance may be achieved from the use of the approach when the labelled data do not adequately represent the entire class distributions. The experimental investigations performed have shown that the approach proposed may be successfully used to train neural networks for learning different classification problems.