Exact inference procedures in Bayesian networks can be expressed using relational algebra; this provides a common ground for optimizations from the AI and database communities. Specifically, the ability to accomodate sparse representations of probability distributions opens up the way to optimize for their cardinality instead of the dimensionality; we apply this in a sensor data model.
|Name||CTIT Technical Report Series|
|Publisher||Centre for Telematics and Information Technology, University of Twente|
- Probabilistic inference
- Bayesian networks
- Relational algebra
- Sensor data