Benchpress: a scalable and platform-independent workflow for benchmarking structure learning algorithms for graphical models.
Felix L. RiosGiusi MoffaJack KuipersPublished in: CoRR (2021)
Keyphrases
- graphical models
- platform independent
- graph structure
- belief propagation
- learning algorithm
- probabilistic model
- random variables
- gaussian graphical models
- probabilistic inference
- bayesian networks
- directed acyclic
- graphical structure
- probabilistic graphical models
- undirected graphical models
- conditional random fields
- approximate inference
- structure learning
- factor graphs
- map inference
- exact inference
- machine learning
- conditional independence
- belief networks
- markov networks
- efficient inference algorithms
- markov logic networks
- business processes
- web services
- hidden variables
- reverse engineering
- message passing
- black box
- reinforcement learning
- metadata