Approximate text search is a basic technique to handle recognized text that contains recognition errors. This paper proposes an approximate string search for recognized text using...
We introduce standardised building blocks designed to be used with variational Bayesian learning. The blocks include Gaussian variables, summation, multiplication, nonlinearity, a...
Tapani Raiko, Harri Valpola, Markus Harva, Juha Ka...
The management of big databases of threedimensional models (used in CAD applications, visualization, games, etc.) is a very important domain. The ability to characterize and easil...
The management of big databases of three-dimensional models (used in CAD applications, visualization, games, etc.) is a very important domain. The ability to characterize and easi...
Time-series segmentation in the fully unsupervised scenario in which the number of segment-types is a priori unknown is a fundamental problem in many applications. We propose a Ba...