Welcome to the Alchemy system! Alchemy is a software package providing
a series of algorithms for statistical relational learning and
probabilistic logic inference, based on the Markov logic representation.
Alchemy allows you to easily develop a wide range of AI applications,
including:
- Collective classification
- Link prediction
- Entity resolution
- Social network modeling
- Information extraction
If you are not already familiar with Markov logic,
we recommend that you first read the paper
Unifying Logical and Statistical AI.
The beta version of Alchemy is now available.
It includes:
- Discriminative weight learning (Voted Perceptron, Conjugate Gradient, and Newton's Method)
- Generative weight learning
- Structure learning
- MAP/MPE inference (including memory efficient)
- Probabilistic inference (including memory efficient): MC-SAT, Gibbs Sampling,
Simulated Tempering
- Support for native and linked-in functions
- Block inference and learning over variables with mutually exclusive
and exhaustive values
- EM (to handle ground atoms with unknown truth values during learning)
In the next release we plan to include:
- Lifted inference
- Online inference and learning
- Specification of indivisible formulas (i.e. formulas that should not be
broken up into separate clauses)
- Exact inference for small domains
- Specification of probabilities instead of weights for formulas in an MLN,
and of probabilities for ground atoms in a database
- Support of continuous features and domains
- Decision Theory
- More extensive documentation
Email us with questions, bug reports, feature requests, etc. at
<the system name> at cs dot washington dot edu.
Alchemy is funded by:
