#### Filter Results:

- Full text PDF available (38)

#### Publication Year

1992

2017

- This year (2)
- Last 5 years (11)
- Last 10 years (20)

#### Publication Type

#### Co-author

#### Journals and Conferences

#### Data Set Used

#### Key Phrases

Learn More

- Jue Wang, Bo Thiesson, Ying-Qing Xu, Michael F. Cohen
- ECCV
- 2004

Mean shift is a nonparametric estimator of density which has been applied to image and video segmentation. Traditional mean shift based segmentation uses a radially symmetric kernel to estimate local density, which is not optimal in view of the often structured nature of image and more particularly video data. In this paper we present an anisotropic kernel… (More)

- Bo Thiesson, Christopher Meek, David Heckerman
- Machine Learning
- 2001

The EM algorithm is a popular method for parameter estimation in a variety of problems involving missing data. However, the EM algorithm often requires significant computational resources and has been dismissed as impractical for large databases. We present two approaches that significantly reduce the computational cost of applying the EM algorithm to… (More)

- Christopher Meek, Bo Thiesson, David Heckerman
- Journal of Machine Learning Research
- 2002

We examine the learning-curve sampling method, an approach for applying machinelearning algorithms to large data sets. The approach is based on the observation that the computational cost of learning a model increases as a function of the sample size of the training data, whereas the accuracy of a model has diminishing improvements as a function of sample… (More)

We describe a heuristic method for learning mixtures of Bayesian Networks (MBNs) from possibly incomplete data. The considered class of models is mixtures in which each mixture component is a Bayesian network encoding a conditional Gaussian distribution over a xed set of variables. Some variables may be hidden or otherwise have missing observations. A key… (More)

- Bo Thiesson
- UAI
- 1997

Recursive graphical models usually under lie the statistical modelling concerning prob abilistic expert systems based on Bayesian networks. This paper defines a version of these models, denoted as recursive exponen tial models, which have evolved by the de sire to impose sophisticated domain knowl edge onto local fragments of a model. Besides the… (More)

- Bo Thiesson
- 1995

Probabilistic expert systems based on Bayesian networks (BNs) require initial speciication of both a qualitative graphical structure and quantitative assessment of conditional probability tables. This paper considers statistical batch learning of the probability tables on the basis of incomplete data and expert knowledge. The EM algorithm with a generalized… (More)

We express the classic ARMA time-series model as a directed graphical model. In doing so, we find that the deterministic relationships in the model make it effectively impossible to use the EM algorithm for learning model parameters. To remedy this problem, we replace the deterministic relationships with Gaussian distributions having a small variance,… (More)

We describe computationally efficient meth ods for learning mixtures in which each com ponent is a directed acyclic graphical model (mixtures of DAGs or MDAGs). We argue that simple search-and-score algorithms are infeasible for a variety of problems, and in troduce a feasible approach in which param eter and structure search is interleaved and expected… (More)

- Bo Thiesson
- 1993

The theoretical background for a program for establishing expert systems on the basis of observations and expert knowledge is presented. Block recur-sive models form the basis of the statistical modelling. These models, together with various model selection methods for automatic model selection, are presented. Additionally, the connection between a block… (More)

- Bo Thiesson
- KDD
- 1995

Probabilistic expert systems based on Bayesian networks (BNs) require initial specification both a qualitative graphical structure and quantitative assessment of conditional probability tables. This paper considers statistical batch learning of the probability tables on the basis of incomplete data and expert knowledge. The EM algorithm with a generalized… (More)