1 code implementation • 3 Nov 2020 • Charupriya Sharma, Zhenyu A. Liao, James Cussens, Peter van Beek
A Bayesian network can be learned from data using the well-known score-and-search approach, and within this approach a key consideration is how to simultaneously learn the global structure in the form of the underlying DAG and the local structure in the CPDs.
no code implementations • 27 Aug 2020 • Zhenyu A. Liao, Charupriya Sharma, James Cussens, Peter van Beek
However, selecting a single model (i. e., the best scoring BN) can be misleading or may not achieve the best possible accuracy.
no code implementations • 7 Oct 2019 • Teny Handhayani, James Cussens
The advantage of this idea is that is possible to handle any data type by using a suitable kernel function to compute a kernel matrix for an observed variable.
1 code implementation • 23 May 2019 • Alvaro H. C. Correia, James Cussens, Cassio de Campos
Many algorithms for score-based Bayesian network structure learning (BNSL), in particular exact ones, take as input a collection of potentially optimal parent sets for each variable in the data.
no code implementations • 30 Apr 2019 • Durdane Kocacoban, James Cussens
We present two online causal structure learning algorithms which can track changes in a causal structure and process data in a dynamic real-time manner.
no code implementations • 12 Nov 2018 • Zhenyu A. Liao, Charupriya Sharma, James Cussens, Peter van Beek
However, selecting a single model (i. e., the best scoring BN) can be misleading or may not achieve the best possible accuracy.
no code implementations • 14 Aug 2018 • James Cussens
Given (1) a set of clauses $T$ in some first-order language $\cal L$ and (2) a cost function $c : B_{{\cal L}} \rightarrow \mathbb{R}_{+}$, mapping each ground atom in the Herbrand base $B_{{\cal L}}$ to a non-negative real, then the problem of finding a minimal cost Herbrand model is to either find a Herbrand model $\cal I$ of $T$ which is guaranteed to minimise the sum of the costs of true ground atoms, or establish that there is no Herbrand model for $T$.
no code implementations • 13 May 2016 • James Cussens, Matti Järvisalo, Janne H. Korhonen, Mark Bartlett
The challenging task of learning structures of probabilistic graphical models is an important problem within modern AI research.
no code implementations • 10 Jul 2015 • James Cussens
Finding the most probable (MAP) model in SRL frameworks such as Markov logic and Problog can, in principle, be solved by encoding the problem as a `grounded-out' mixed integer program (MIP).
no code implementations • 4 Apr 2014 • Chris. J. Oates, Jim Q. Smith, Sach Mukherjee, James Cussens
This paper considers the problem of estimating the structure of multiple related directed acyclic graph (DAG) models.
no code implementations • 26 Sep 2013 • Mark Bartlett, James Cussens
We consider the problem of learning Bayesian networks (BNs) from complete discrete data.
no code implementations • 14 Feb 2012 • James Cussens
The problem of learning the structure of Bayesian networks from complete discrete data with a limit on parent set size is considered.