Semi-supervised learning with Bayesian Confidence Propagation Neural Network

Naresh Balaji Ravichandran, Anders Lansner, Pawel Herman
2021 ESANN 2021 proceedings   unpublished
Learning internal representations from data using no or few labels is useful for machine learning research, as it allows using massive amounts of unlabeled data. In this work, we use the Bayesian Confidence Propagation Neural Network (BCPNN) model developed as a biologically plausible model of the cortex. Recent work has demonstrated that these networks can learn useful internal representations from data using local Bayesian-Hebbian learning rules. In this work, we show how such representations
more » ... can be leveraged in a semi-supervised setting by introducing and comparing different classifiers. We also evaluate and compare such networks with other popular semi-supervised classifiers. *
doi:10.14428/esann/2021.es2021-156 fatcat:j32t6nbsc5gcjluy3jdhaclbma