Kommende Vorträge

Hybrid. Contact: Christian Kaiser (kaiser @ mpim-bonn.mpg.de)

Contact: Aru Ray (aruray @ mpim-bonn.mpg.de)

In machine learning, a fundamental problem is to construct good feature maps for data. Such feature maps should allow us to approximate functions and characterise probability measures on the data space. In many applications, the data themselves come in the form of functions, equipped with additional structure, and the feature map should preserve this structure. For instance, time series data are viewed as maps from an interval into a vector space, while images can be interpreted as maps from a square into a vector space.

Let $k\geq 2$. A generalization of the well-known Pell sequence is the $k$-Pell sequence whose first $k$ terms are $0,\ldots,0,1$  and each term afterwards is given by the linear recurrence  $$P_n^{(k)}=2P_{n-1}^{(k)}+P_{n-2}^{(k)}+\cdots +P_{n-k}^{(k)}.$$