1 code implementation • EuroMLSys 2023 • Mehran Salmani, Saeid Ghafouri, Alireza Sanaee, Kamran Razavi, Max Mühlhäuser, Joseph Doyle, Pooyan Jamshidi, Mohsen Sharifi
Adapting to dynamic workloads considering all the pillars of accuracy, latency, and resource cost is challenging.
no code implementations • 12 Jan 2023 • Thomas Kreutz, Ousama Esbel, Max Mühlhäuser, Alejandro Sanchez Guinea
With our approach, we evaluate the applicability of recent time series-related contrastive and generative SSL techniques to learn representations that distinguish driving events.
1 code implementation • 30 Dec 2022 • Thomas Kreutz, Max Mühlhäuser, Alejandro Sanchez Guinea
In this work, we address the problem of unsupervised moving object segmentation (MOS) in 4D LiDAR data recorded from a stationary sensor, where no ground truth annotations are involved.
2 code implementations • 19 May 2021 • Aidmar Wainakh, Fabrizio Ventola, Till Müßig, Jens Keim, Carlos Garcia Cordero, Ephraim Zimmer, Tim Grube, Kristian Kersting, Max Mühlhäuser
Specifically, we investigate Label Leakage from Gradients (LLG), a novel attack to extract the labels of the users' training data from their shared gradients.
no code implementations • 23 Apr 2020 • Aidmar Wainakh, Alejandro Sanchez Guinea, Tim Grube, Max Mühlhäuser
Federated learning suffers from several privacy-related issues that expose the participants to various threats.
Cryptography and Security
2 code implementations • 29 Nov 2019 • Timo Nolle, Alexander Seeliger, Nils Thoma, Max Mühlhäuser
In this paper, we propose DeepAlign, a novel approach to multi-perspective process anomaly correction, based on recurrent neural networks and bidirectional beam search.
3 code implementations • 8 Feb 2019 • Timo Nolle, Stefan Luettgen, Alexander Seeliger, Max Mühlhäuser
Finally, we demonstrate that a simple set of rules can be used to utilize the output of BINet for anomaly classification.
no code implementations • 3 Mar 2018 • Timo Nolle, Stefan Luettgen, Alexander Seeliger, Max Mühlhäuser
In this paper, we propose a method, using autoencoders, for detecting and analyzing anomalies occurring in the execution of a business process.
1 code implementation • International Conference on Text, Speech, and Dialogue 2015 • Stephan Radeck-Arneth, Benjamin Milde, Arvid Lange, Evandro Gouvea, Stefan Radomski, Max Mühlhäuser, and Chris Biemann
We present a new freely available corpus for German distant speech recognition and report speaker-independent word error rate (WER) results for two open source speech recognizers trained on this corpus.
Ranked #8 on Speech Recognition on TUDA