Die Dozenten der Informatik-Institute der Technischen Universität
Braunschweig laden im Rahmen des Informatik-Kolloquiums zu folgendem
Vortrag ein.
Prof. Dr. Joachim M. Buhmann, ETH Zürich, Lehrstuhl für Information
Science & Engineering:
Big Data: where is the information
Beginn: 13.08.2013, 10:00 Uhr
Ort: TU Braunschweig, Informatikzentrum, Mühlenpfordtstraße 23,
Galeriegeschoss, Raum G04
Webseite: http://www.ibr.cs.tu-bs.de/cal/kolloq/2013-08-13-buhmann.html
Kontakt: Prof. Dr.-Ing. F. M. Wahl
The digital revolution has created unprecedented opportunities in
computing and communication but it also has generated the data deluge with
an urgent demand for new pattern recognition technology. Learning patterns
in data requires to extract interesting, statistically significant
regularities in (large) data sets, e.g. the identification of connection
patterns in the brain (connectomics) or the detection of cancer cells
in tissue microarrays and estimating their staining as a cancer severity
score. Admissible solutions or hypotheses specify the context of pattern
analysis problems which have to cope with model mismatch and noise in
data. An information theoretic approach is developed which estimates
the precision of inferred solution sets and regularizes solutions
in a noise adapted way. The tradeoff between "informativeness" and
"robustness" is mirrored by the balance between high information content
and identifiability of solution sets, thereby giving rise to a new notion
of context sensitive information. Cost function to rank solutions and,
more abstractly, algorithms are considered as noisy channels with an
approximation capacity. The effectiveness of this concept is demonstrated
by model validation for spectral clustering based on different variants
of graph cuts. The concept also enables us to measure how many bit are
extracted by sorting algorithms when the input and thereby the pairwise
comparisons are subject to fluctuations.
