I am looking to implement statistical relational learning, preferably in a modern programming language, and came across Factorie and Figaro for Scala. But most resources online that compare these are a little outdated, since these are under active development.
How does Factorie compare against Figaro now? (and how do these compare against the C++ based Alchemy?)
Some features that I would like to seem compared on are:
- Directed (Bayesian Logic) and Undirected (Markov Logic) graphical models
- Inductive and deductive inference algorithms for first order logic
- Learning algorithms
- Support for Dynamic, time-series algorithms (for first order logical inference)
- Support for higher order (probabilistic) logic