Schwarz, Wallace, and Rissanen: Intertwining Themes in Theories of Model Selection

Lanterman, Aaron D.

doi:10.2307/1403813

Cited by 34 publications

(39 citation statements)

References 42 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Both P3 and ACC deficits during executive control belong to the most common findings in schizophrenia (e.g., Carter , 2001;Bramon et al, 2004;Kerns et al, 2005). The fact that both target conditions were associated with cingulate deficits in schizophrenic patients supports two arguments.…”

Section: Mean Rt [Ms]mentioning

confidence: 88%

See 1 more Smart Citation

Single-subject classification of schizophrenia by event-related potentials during selective attention

et al. 2011

View full text Add to dashboard Cite

Section: Mean Rt [Ms]mentioning

confidence: 88%

“…However, with only 80 samples given, doing so would be an exercise in over-fit; moreover, some classifiers may work better by pure chance, even if CV scores were used (Lanterman, 2001). The goal of the present study was to investigate which features are critical for establishing the difference among groups.…”

Section: Mean Rt [Ms]mentioning

confidence: 99%

Single-subject classification of schizophrenia by event-related potentials during selective attention

et al. 2011

View full text Add to dashboard Cite

“…Each criterion has its own characteristics. For a detailed overview about the most used ones, refer to [24]. A common feature is that all of them tend to penalize complex models.…”

Section: Em Algorithm: Model Selection Criteriamentioning

confidence: 99%

Fast estimation of Gaussian mixture models for image segmentation

Greggio

Bernardino

Laschi

et al. 2011

Machine Vision and Applications

View full text Add to dashboard Cite

The expectation maximization algorithm has been classically used to find the maximum likelihood estimates of parameters in probabilistic models with unobserved data, for instance, mixture models. A key issue in such problems is the choice of the model complexity. The higher the number of components in the mixture, the higher will be the data likelihood, but also the higher will be the computational burden and data overfitting. In this work, we propose a clustering method based on the expectation maximization algorithm that adapts online the number of components of a finite Gaussian mixture model from multivariate data or method estimates the number of components and their means and covariances sequentially, without requiring any careful initialization. Our methodology starts from a single mixture component covering the whole data set and sequentially splits it incrementally during expectation maximization steps. The coarse to fine nature of the algorithm reduce the overall number of computations to achieve a solution, which makes the method particularly suited to image segmentation applications whenever computational time is an issue. We show the effectiveness of the method in a series of experiments and compare it with a state-of-the-art alternative technique both with synthetic data and real images, including experiments with images acquired from the iCub humanoid robot.

show abstract

“…The rationale of MML criterion is: the shorter the encoding message length for data is, the better the corresponding data generation model is. For detailed accounts on MML criterion (see Figueiredo and Jain 2002;Lanterman 2001;Nascimento et al 2010;Hanlon and Forbes 2002).…”

Section: Criterion For Gg Clustering-based Time Series Segmentatimentioning

confidence: 99%

Improved Gath–Geva clustering for fuzzy segmentation of hydrometeorological time series

Wang

Liu

Yin

2011

Stoch Environ Res Risk Assess

View full text Add to dashboard Cite

In this paper, an improved Gath-Geva clustering algorithm is proposed for automatic fuzzy segmentation of univariate and multivariate hydrometeorological time series. The algorithm considers time series segmentation problem as Gath-Geva clustering with the minimum message length criterion as segmentation order selection criterion. One characteristic of the improved Gath-Geva clustering algorithm is its unsupervised nature which can automatically determine the optimal segmentation order. Another characteristic is the application of the modified component-wise expectation maximization algorithm in Gath-Geva clustering which can avoid the drawbacks of the classical expectation maximization algorithm: the sensitivity to initialization and the need to avoid the boundary of the parameter space. The other characteristic is the improvement of numerical stability by integrating segmentation order selection into model parameter estimation procedure. The proposed algorithm has been experimentally tested on artificial and hydrometeorological time series. The obtained experimental results show the effectiveness of our proposed algorithm.

show abstract

Schwarz, Wallace, and Rissanen: Intertwining Themes in Theories of Model Selection

Cited by 34 publications

References 42 publications

Single-subject classification of schizophrenia by event-related potentials during selective attention

Single-subject classification of schizophrenia by event-related potentials during selective attention

Fast estimation of Gaussian mixture models for image segmentation

Improved Gath–Geva clustering for fuzzy segmentation of hydrometeorological time series

Contact Info

Product

Resources

About