| Saturday 27 April 2024 | |
| Events for day: Thursday 15 November 2018 |
| 10:00 - 11:00 Weekly Seminar Introducing some new methods for learning Bayesian network structure School BIOLOGICAL SCIENCES Bayesian networks (BNs) are directed acyclic graphs (DAGs), where the nodes are random variables, and the arcs specify the independence assumptions. The learning task in a BN can be separated into two subtasks; structure learning that is to identify the topology of the network, and parameter learning which is the conditional probabilities for a given network topology. Learning a BN is the problem of finding the structure of the DAG that best matches the dataset. The search space of all BN structure is extremely large. It has been shown that the number of different structure grows super-exponential with respect to the number of nodes. T ... |