The Resolved Mutual Information Function as a Structural Fingerprint of Biomolecular Sequences for Interpretable Machine Learning Classifiers

Autor: Katrin Sophie Bohnsack, Marika Kaden, Julia Abel, Sascha Saralajew, Thomas Villmann

Publikováno v: Entropy, Vol 23, Iss 10, p 1357 (2021)

In the present article we propose the application of variants of the mutual information function as characteristic fingerprints of biomolecular sequences for classification analysis. In particular, we consider the resolved mutual information function

Externí odkaz: https://doaj.org/article/a6eacff6bfc84d1b8f3d1355b0745cc6

Variants of DropConnect in Learning vector quantization networks for evaluation of classification stability

Autor: Jensun Ravichandran, Marika Kaden, Sascha Saralajew, Thomas Villmann

Publikováno v: Neurocomputing. 403:121-132

Dropout and DropConnect are useful methods to prevent multilayer neural networks from overfitting. In addition, it turns out that these tools can also be used to estimate the stability of networks regarding disturbances. Prototype based networks gain

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::20ae9de72461efed3a69f1a09fc861a1
https://doi.org/10.1016/j.neucom.2019.12.131

Radar Artifact Labeling Framework (RALF): Method for Plausible Radar Detections in Datasets

Autor: J. Zoellner, Sascha Saralajew, Fabian Klein, Marcel Schilling, Simon Isele

Publikováno v: Proceedings of the 7th International Conference on Vehicle Technology and Intelligent Transport Systems.

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::39aaed6550dfc00c6a3d4f337a271418
https://doi.org/10.5220/0010395100002932

The coming of age of interpretable and explainable machine learning models

Autor: Sascha Saralajew, Alfredo Vellido, Thomas Villmann, Paulo J. G. Lisboa

Publikováno v: ESANN 2021 proceedings European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
UPCommons. Portal del coneixement obert de la UPC
Universitat Politècnica de Catalunya (UPC)

Machine learning-based systems are now part of a wide array of real-world applications seamlessly embedded in the social realm. In the wake of this realisation, strict legal regulations for these systems are currently being developed, addressing some

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::374e0d40f7d711046def103558f8baba
https://hdl.handle.net/2117/368022

Provident Detection of Vehicles at Night

Autor: Sascha Saralajew, Lars Ohnemus, Emilio Oldenziel

Publikováno v: IV

Visual perception is one of the most important information sources during driving. However, current camera perception systems are limited to object detection and, hence, to directly visible objects. Because it is mandatory for vehicles to run headlig

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::94f75c524972f73b3f00874d1eda6f95
https://doi.org/10.1109/iv47402.2020.9304752