Match!
Marina M.-C. Vidovic
Technical University of Berlin
6Publications
4H-index
53Citations
Publications 6
Newest
#1Marina M.-C. Vidovic (Technical University of Berlin)H-Index: 4
#2Marius Kloft (Humboldt University of Berlin)H-Index: 18
Last.Nico Görnitz (Technical University of Berlin)H-Index: 9
view all 4 authors...
High prediction accuracies are not the only objective to consider when solving problems using machine learning. Instead, particular scientific applications require some explanation of the learned prediction function. For computational biology, positional oligomer importance matrices (POIMs) have been successfully applied to explain the decision of support vector machines (SVMs) using weighted-degree (WD) kernels. To extract relevant biological motifs from POIMs, the motifPOIM method has been dev...
#1Marina M.-C. Vidovic (Technical University of Berlin)H-Index: 4
#2Han-Jeong Hwang (Technical University of Berlin)H-Index: 16
Last.Klaus-Robert Müller (Technical University of Berlin)H-Index: 4
view all 6 authors...
Fundamental changes over time of surface EMG signal characteristics are a challenge for myocontrol algorithms controlling prosthetic devices. These changes are generally caused by electrode shifts after donning and doffing, sweating, additional weight or varying arm positions, which results in a change of the signal distribution - a scenario often referred to as covariate shift. A substantial decrease in classification accuracy due to these factors hinders the possibility to directly translate E...
#2Nico GörnitzH-Index: 9
Last.Marius KloftH-Index: 18
view all 4 authors...
Complex problems may require sophisticated, non-linear learning methods such as kernel machines or deep neural networks to achieve state of the art prediction accuracies. However, high prediction accuracies are not the only objective to consider when solving problems using machine learning. Instead, particular scientific applications require some explanation of the learned prediction function. Unfortunately, most methods do not come with out of the box straight forward interpretation. Even linea...
#1Marina M.-C. Vidovic (Technical University of Berlin)H-Index: 4
#2Nico Görnitz (Technical University of Berlin)H-Index: 9
Last.Marius Kloft (Humboldt University of Berlin)H-Index: 18
view all 5 authors...
Identifying discriminative motifs underlying the functionality and evolution of organisms is a major challenge in computational biology. Machine learning approaches such as support vector machines (SVMs) achieve state-of-the-art performances in genomic discrimination tasks, but—due to its black-box character—motifs underlying its decision function are largely unknown. As a remedy, positional oligomer importance matrices (POIMs) allow us to visualize the significance of position-specific subseque...
#2Nico GörnitzH-Index: 9
Last.Marius Kloft (Humboldt University of Berlin)H-Index: 18
view all 5 authors...
This work is in the context of kernel-based learning algorithms for sequence data. We present a probabilistic approach to automatically extract, from the output of such string-kernel-based learning algorithms, the subsequences--or motifs--truly underlying the machine's predictions. The proposed framework views motifs as free parameters in a probabilistic model, which is solved through a global optimization approach. In contrast to prevalent approaches, the proposed method can discover even diffi...
Aug 1, 2014 in EMBC (International Conference of the IEEE Engineering in Medicine and Biology Society)
#1Marina M.-C. Vidovic (Technical University of Berlin)H-Index: 4
#2Liliana P. ParedesH-Index: 6
Last.Klaus-Robert Müller (Technical University of Berlin)H-Index: 4
view all 9 authors...
1