|
|
aGrUM is a C++ library designed for easily building applications using graphical models such as Bayesian networks, influence diagrams, decision trees, GAI networks or Markov decision processes.
|
|
|
|
|
|
aGrUM is written to provide the basic building blocks to perform the following tasks :
|
|
|
|
|
|
* designing graphical models,
|
|
|
* learning graphical models,
|
|
|
* elicitation of graphical models,
|
|
|
* inference within graphical models,
|
|
|
* planning
|
|
|
|
|
|
# Functionalities
|
|
|
|
|
|
<table>
|
|
|
<tr><th>Model</th><th>Domain</th><th>Algorithm</th></tr>
|
|
|
<tr><td rowspan="5">Bayesian Network</td><td>Input/Output</td><td> bif/bifxml/dsl/net formats (read/write)</td></tr>
|
|
|
<tr><td>Exact Inference with Relevant Reasonning </td><td> Variable Elimination Shafer-Shenoy Inference Lazy Propagation </td></tr>
|
|
|
<tr><td>Approximated Inference</td><td>Gibbs Sampling, Loopy Belief Propagation</td></tr>
|
|
|
<tr><td>Parameter Learning</td><td>Pure maxLikelihood, Laplace, Dirichlet </td></tr>
|
|
|
<tr><td> Structural Learning</td><td>Local search with Tabu List Greedy Hill Climbing K2 constraints : mandatory/forbidden arcs,etc.</td></tr>
|
|
|
</table>
|
|
|
|
|
|
| Bayesian Network | Input/Output | bif/bifxml/dsl/net formats (read/write) |
|
|
|
|
|
|
| Parameter Learning | Pure maxLikelihood,
|
|
|
Laplace,
|
|
|
Dirichlet |
|
|
|
| Structural Learning | Local search with Tabu List
|
|
|
Greedy Hill Climbing
|
|
|
K2
|
|
|
constraints : mandatory/forbidden arcs,etc.|
|
|
|
| Miscellenaous | Exact and *approximated* distance/divergence between BNs (KL, Bhattacharya, Hellinger)
|
|
|
Mutual information, entropy,
|
|
|
Simulation (generation of csv files),
|
|
|
etc. |
|
|
|
|/2=. Influence Diagram | Input/Output | bifxml |
|
|
|
| Inference | Junction Trees |
|
|
|
|/2=. Probabilistic Relational Model | Input/output | *O3PRM language parser*|
|
|
|
| Exact inference | *Structured Variable Elimination* (SVE) |
|
|
|
|=. Credal Networks | Approximated inference | GL2U
|
|
|
*MC Sampling* |
|
|
|
|/3=. FMDP | Input | |
|
|
|
| Planning | SVI
|
|
|
SPUDD |
|
|
|
| multi-valued Decision Diagram | *SPUnDD* |
|
|
|
|
|
|
*Legend* :
|
|
|
* _Mandatory algorithms_ before 1.0.0
|
|
|
* *specific* algorithms in aGrUM
|
|
|
|
|
|
h2. Installation
|
|
|
|
|
|
* For Linux scientists : [[LinuxInstall]]
|
|
|
* For Windows users : [[WindowsInstall]]
|
|
|
* For Mac geeks : [[MacInstall]]
|
|
|
|
|
|
h2. Documentation & supports
|
|
|
|
|
|
* "Doxygen documentation":http://www-desir.lip6.fr/~phw/aGrUM/officiel/doxygen/ of aGrUM
|
|
|
* mailing list : https://mailia.lip6.fr/wws/info/agrum-users
|
|
|
|
|
|
* "Minimal project using cmake":http://www-desir.lip6.fr/~phw/aGrUM/officiel/doxygen/db/db6/using_agrum.html in the online documentation
|
|
|
|
|
|
* Some [[agrumdecisiondeck.pdf|slides]] on aGrUM by "Christophe Gonzales":http://www-desir.lip6.fr/mbr_Christophe_Gonzales.html for the "Decision Deck Consortium":http://sma.uni.lu/d2cms/tiki-index.php?page=Decision+Deck+Consortium.
|
|
|
|
|
|
* [[FAQ]]
|
|
|
|
|
|
h2. People & Applications
|
|
|
|
|
|
* [[People]]
|
|
|
* [[PhD Thesis using aGrUM]]
|
|
|
* [[Project and Applications]]
|
|
|
|
|
|
h2. Licence
|
|
|
|
|
|
The contribution agreement can be found [[Contribution|here]].
|
|
|
|
|
|
aGrUM is released under the Gnu Public License, which means it can be freely copied and distributed, and costs nothing to use in open-source applications. Especially, aGrUM can be used freely for research project.
|
|
|
|
|
|
If you wish to use aGrUM in a closed-source product, please contact C.Gonzales or P-H.Wuillemin in order to get appropriate licenses. |
|
|
\ No newline at end of file |