This study shows that a mixture of RNN experts model can acquire the ability to generate sequences that are combination of multiple primitive patterns by means of self-organizing ...
We develop nonparametric Bayesian models for multiscale representations of images depicting natural scene categories. Individual features or wavelet coefficients are marginally de...
Jyri J. Kivinen, Erik B. Sudderth, Michael I. Jord...
Many text documents naturally have two kinds of labels. For example, we may label web pages from universities according to their categories, such as "student" or "fa...
Winner-Takes-All (WTA) prescriptions for Learning Vector Quantization (LVQ) are studied in the framework of a model situation: Two competing prototype vectors are updated accordin...
In this paper, we propose an approach to learning appearance models of moving objects directly from compressed video. The appearance of a moving object changes dynamically in vide...