TU Berlin

Neural Information ProcessingLearning on Structured Representations

Neuronale Informationsverarbeitung

Page Content

to Navigation

Learning on Structured Representations


Learning from examples in order to predict is one of the standard tasks in machine learning. Many techniques have been developed to solve classification and regression problems, but by far, most of them were specifically designed for vectorial data. Vectorial data are very convenient because of the structure imposed by the Euclidean metric. For many data sets (protein sequences, text, images, videos, chemical formulas, etc.) a vector-based description is not only inconvenient but may simply wrong, and representations that consider relationships between objects or that embed objects in spaces with non-Euclidean structure are often more appropriate. Here we follow different approaches to extend learning from examples to non-vectorial data. One approach is focussed on an extension of kernel methods leading to learning algorithms specifically designed for relational data representations of a general form. In a second approach - specifically designed for objects which are naturally represented in terms of finite combinatorial structures - we explore embeddings into quotient spaces of a Euclidean vector space ("structure spaces"). In a third approach we consider representations of in spaces with data adapted geometries, i.e. using Riemannian manifolds as models for data spaces. In this context we are also interested in active learning schemes which are based on geometrical concepts. The developed algorithms have been applied to various applications domains, including bio- and chemoinformatics (cf. "Research" page "Applications to Problems in Bio- and Chemoinformatics") and the analysis of multimodal neural data (cf. "Research" page "MRI, EM, Autoradiography, and Multi-modal Data").

Acknowledgement: This work was funded by the BMWA and by the Technical University of Berlin.


The Potential Support Vector Machine (P-SVM)

Selected Publications:

Robust Detection of Environmental Sounds in Binaural Auditory Scenes
Citation key Trowitzsch2017Robust
Author Trowitzsch, I., and Mohr, J., and Kashef, Y., and Obermayer, K.
Pages 1344-1356
Year 2017
ISSN 2329-9304
DOI 10.1109/TASLP.2017.2690573
Journal IEEE Transactions on Audio Speech and Language Processing
Volume 25
Number 6
Bibtex Type of Publication Selected:structured selected:publications selected:main
Download Bibtex entry


Quick Access

Schnellnavigation zur Seite über Nummerneingabe