The practice of qualitative parameterisation in the development of Bayesian networks
The typical phases of Bayesian network (BN) structured development include specification of purpose and scope, structure development, parameterisation and validation. Structure development is typically focused on qualitative issues and parameterisation quantitative issues, however there are qualitative and quantitative issues that arise in both phases. A common step that occurs after the initial structure has been developed is to perform a rough parameterisation that only captures and illustrates the intended qualitative behaviour of the model. This is done prior to a more rigorous parameterisation, ensuring that the structure is fit for purpose, as well as supporting later development and validation. In our collective experience and in discussions with other modellers, this step is an important part of the development process, but is under-reported in the literature. Since the practice focuses on qualitative issues, despite being quantitative in nature, we call this step qualitative parameterisation and provide an outline of its role in the BN development process.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Structural Refinement of Bayesian Networks for Efficient Model Parameterisation
Many Bayesian network modelling applications suffer from the issue of data scarcity. Hence the use of expert judgement often becomes necessary to determine the parameters of the conditional probability tables (CPTs) thro…
Rao-Blackwellised Reparameterisation Gradients
Latent Gaussian variables have been popularised in probabilistic machine learning. In turn, gradient estimators are the machinery that facilitates gradient-based optimisation for models with latent Gaussian variables. Th…
Variational InferenceMachine Learning-Assisted Discovery of Flow Reactor Designs
Additive manufacturing has enabled the fabrication of advanced reactor geometries, permitting larger, more complex design spaces. Identifying promising configurations within such spaces presents a significant challenge f…
Bayesian OptimisationDiagonalisation SGD: Fast & Convergent SGD for Non-Differentiable Models via Reparameterisation and Smoothing
It is well-known that the reparameterisation gradient estimator, which exhibits low variance in practice, is biased for non-differentiable models. This may compromise correctness of gradient-based optimisation methods su…
Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration
Hyperparameter tuning can dramatically impact training stability and final performance of large-scale models. Recent works on neural network parameterisations, such as $μ$P, have enabled transfer of optimal global hyperp…