Semi-supervised learning with Bayesian Confidence Propagation Neural Network

• 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. 

Subject headings

SAMHÄLLSVETENSKAP  -- Ekonomi och näringsliv -- Företagsekonomi (hsv//swe)

SOCIAL SCIENCES  -- Economics and Business -- Business Administration (hsv//eng)

TEKNIK OCH TEKNOLOGIER  -- Elektroteknik och elektronik -- Robotteknik och automation (hsv//swe)

ENGINEERING AND TECHNOLOGY  -- Electrical Engineering, Electronic Engineering, Information Engineering -- Robotics (hsv//eng)

NATURVETENSKAP  -- Data- och informationsvetenskap -- Språkteknologi (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Language Technology (hsv//eng)

Keyword

Backpropagation

Neural networks

Torsional stress

Bayesian

Cortexes

Internal representation

Learn

Machine learning research

Neural network model

Neural-networks

Plausible model

Semi-supervised

Unlabeled data

Bayesian networks

Publication and Content Type

ref (subject category)

kon (subject category)