Machine Learning with BayesiaLab

BayesiaLab includes a broad set of optimized algorithms for learning Bayesian networks from data, including both structure and parameters.

• Many learning criteria are information-theoretic (for example, Minimum Description Length).
• The workflows do not require distributional assumptions.
• The approach scales from small studies to high-dimensional domains.

Unsupervised Structural Learning

• BayesiaLab discovers probabilistic structure without predefining input/output roles.
• This supports data-driven knowledge discovery in unfamiliar domains.

Supervised Learning

• Supervised workflows target predictive performance for a chosen target variable.
• BayesiaLab is not limited to a single network class such as Naive Bayes.
• Algorithms search for high-performing models while controlling structural complexity.
• Markov Blanket methods are especially useful for fast variable selection in high-dimensional settings.

Clustering Workflows

• BayesiaLab supports both Data Clustering and Variable Clustering.
• Data Clustering creates latent variables whose states represent groups of records.
• Variable Clustering groups variables by relationship strength.
• Multiple Clustering combines both approaches in BayesiaLab’s Probabilistic Structural Equation Model workflow.