Nacionalni portal odprte znanosti

In this talk, we are going to see the basics of kernels methods. After a brief presentation of a very simple kernel classifier, we'll give the definition of a postive definite kernel and explain Support vector machine learning. Then, a few kernels for structured data, namely sequences and graphs, wi ...

This paper provides the first - to the best of our knowledge - analysis of online learning algorithms for multiclass problems when the {\em confusion} matrix is taken as a performance measure. The work builds upon recent and elegant results on noncommutative concentration inequalities, i.e. concentr ...

Pac-Bayes bounds are among the most accurate generalization bounds for classifiers learned with \iid data, and it is particularly so for margin classifiers. However, there are many practical cases where the training data show some dependencies and where the traditional \iid assumption does not apply ...

We provide new concentration inequalities for functions of dependent variables. The work extends that of Janson (2004), which proposes concentration inequalities using a combination of the Laplace transform and the idea of fractional graph coloring, as well as many works that derive concentration in ...