Implementing Bayesian Network Induction
Suitable for:Student, Bachelor or Master project
Bayesian Networks and other graphical models for probabilistic reasoning are usually intuitive to use since their graphical nature allows easier interpretation. Probabilistic reasoning in general can be used for a wide range of scenarios and humans are argued to process information more or less in a probabilistic Bayesian way (subject to approximations of course). Our own inference implementation PRIMO (https://gitlab.ub.uni-bielefeld.de/scs/PRIMO) already allows the use of different kinds of networks as well as inference methods, however it does not support the induction or learning of models from data. If a structure is already known, learning the parameters from data is fairly sim- ple and straightforward. Learning the structure however, can be tricky and there exist many different methods. Depending on the scope (BA, MA or project), students should research and select appropri- ate methods that could be used in the existing codebase or adapt the existing codebase accordingly.
- decent knowledge of Bayesian Networks and probabilistic inference
- proficient knowledge in probability theory