Label Propagation Through Neuronal Synchrony

Date
2010-01-01Author
Quiles, Marcos Gonçalves [UNIFESP]
Zhao, Liang
Breve, Fabricio A.
Rocha, Anderson
Type
Trabalho apresentado em eventoISSN
1098-7576Is part of
2010 International Joint Conference On Neural Networks Ijcnn 2010DOI
10.1109/IJCNN.2010.5596809Metadata
Show full item recordAbstract
Semi-Supervised Learning (SSL) is a machine learning research area aiming the development of techniques which are able to take advantage from both labeled and unlabeled samples. Additionally, most of the times where SSL techniques can be deployed, only a small portion of samples in the data set is labeled. To deal with such situations in a straightforward fashion, in this paper we introduce a semi-supervised learning approach based on neuronal synchrony in a network of coupled integrate-and-fire neurons. For that, we represent the input data set as a graph and model each of its nodes by an integrate-and-fire neuron. Thereafter, we propagate the class labels from the seed samples to unlabeled samples through the graph by means of the emerging synchronization dynamics. Experimentations on synthetic and real data show that the introduced technique achieves good classification results regardless the feature space distribution or geometrical shape.