Heterogeneous and incomplete datasets are common in many real-world applications. The probabilistic nature of the Generative Topographic Mapping (GTM), which only handles complete continuous data originally, offers the ability to extend it to also visualise mixed-type and missing data as suggested in (Bishop et al., 1998a). This paper describes this generalisation of GTM and assesses the result...

We currently know little of the role of the corporate human resource (HR) function in multinational corporations regarding global talent management (GTM). GTM is explored here from two perspectives: increasing global competition for talent, and new forms of international mobility. The first considers the mechanisms of GTM, and the second, individual willingness to be mobile, especially in emerg...

This paper describes our participation in the INTERSPEECH 2009 Emotion Challenge [1]. Starting from our previous experience in the use of automatic classification for the validation of an expressive corpus, we have tackled the difficult task of emotion recognition from speech with real-life data. Our main contribution to this work is related to the classifier sub-challenge, for which we tested ...

We introduce a new unsupervised learning algorithm for kernel-based topographic map formation of heteroscedastic gaussian mixtures that allows for a unified account of distortion error (vector quantization), log-likelihood, and Kullback-Leibler divergence.

Students have trouble using and interpreting topographic maps. Experienced map-users identify patterns of contour lines representing topographic structures and visualize that information in 3D. Novices struggle with both recognizing 2D patterns and visualizing 3D structures from contour lines. In this study, the Pattern Identification group received instruction focused on identifying contour pa...

Several methods to visualize clusters in high-dimensional data sets using the Self-Organizing Map (SOM) have been proposed. However, most of these methods only focus on the information extracted from the model vectors of the SOM. This paper introduces a novel method to visualize the clusters of a SOM based on smoothed data histograms. The method is illustrated using a simple 2-dimensional data ...

For a kernel-based topographic map formation, kMER (kernel-based maximum entropy learning rule) was proposed by Van Hulle, and some effective learning rules related to kMER have been proposed so far with many applications. However, no discusions have been made concerning the determination of the number of units in kMER. This letter describes a unit-pruning rule, which permits automatic contruct...