Semi-supervised learning with Bayesian Confidence Propagation Neural Network
This work addresses the challenge of using massive unlabeled data for machine learning, but it appears incremental as it builds on prior models without introducing major breakthroughs.
The paper tackled the problem of learning from unlabeled data in semi-supervised settings by leveraging biologically plausible neural networks, resulting in the development and comparison of new classifiers that were evaluated against existing methods.
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 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.