Software

Bayes Server are pleased to announce the release of Bayes Server 2.2, a high performance .NET API for Bayesian Networks.

Download evaluation version

Browse help with embedded code samples

Browse resources

Features:

• Calculate the probability of variables given evidence. (e.g. P(A) and P(B) given the evidence.)
• Calculate the joint probability of variables given evidence (e.g. P(A,B), P(B,C) given the evidence)
• Calculate the log-likelihood of the evidence.
• Supports hard, soft/virtual and temporal evidence.
• Continuous nodes/variables (CLG distributions).
• Dynamic Bayesian networks (DBN) for modelling temporal or sequential data.
• Support for multiple variables per node. This allows, for example, the direct specification of mixtures of full covariance Gaussians.
• Relevance optimization. Only distributions relevant to a query are used.
• Evidence propagation. Implicit evidence is inferred from any explicit evidence.
• Support for disconnected networks.
• Missing data support. (Including Dynamic Bayesian networks and nodes with multiple variables.)