Search Results for author: Patrick Mäder

Found 11 papers, 4 papers with code

Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks

no code implementations8 Sep 2023 Daniel Scheliga, Patrick Mäder, Marco Seeland

To preserve the privacy preserving effect of PRECODE, our analysis reveals that variational modeling must be placed early in the network.

Federated Learning Image Classification +1

LiDAR-BEVMTN: Real-Time LiDAR Bird's-Eye View Multi-Task Perception Network for Autonomous Driving

no code implementations17 Jul 2023 Sambit Mohapatra, Senthil Yogamani, Varun Ravi Kumar, Stefan Milz, Heinrich Gotzig, Patrick Mäder

We achieve state-of-the-art results for two tasks, semantic and motion segmentation, and close to state-of-the-art performance for 3D object detection.

3D Object Detection Autonomous Driving +7

Flipped Classroom: Effective Teaching for Time Series Forecasting

1 code implementation17 Oct 2022 Philipp Teutsch, Patrick Mäder

Although scheduled sampling seems to be a convincing alternative to FR and TF, we found that, even if parametrized carefully, scheduled sampling may lead to premature termination of the training when applied for time series forecasting.

Time Series Time Series Forecasting

Generalizability of Code Clone Detection on CodeBERT

no code implementations26 Aug 2022 Tim Sonnekalb, Bernd Gruner, Clemens-Alexander Brust, Patrick Mäder

Transformer networks such as CodeBERT already achieve outstanding results for code clone detection in benchmark datasets, so one could assume that this task has already been solved.

Clone Detection

Dropout is NOT All You Need to Prevent Gradient Leakage

1 code implementation12 Aug 2022 Daniel Scheliga, Patrick Mäder, Marco Seeland

We find that state of the art attacks are not able to reconstruct the client data due to the stochasticity induced by dropout during model training.

Federated Learning Image Classification

Combining Variational Modeling with Partial Gradient Perturbation to Prevent Deep Gradient Leakage

no code implementations9 Aug 2022 Daniel Scheliga, Patrick Mäder, Marco Seeland

In result, we show that our approach requires less gradient perturbation to effectively preserve privacy without harming model performance.

Image Classification Privacy Preserving

Direct data-driven forecast of local turbulent heat flux in Rayleigh-Bénard convection

no code implementations26 Feb 2022 Sandeep Pandey, Philipp Teutsch, Patrick Mäder, Jörg Schumacher

A combined convolutional autoencoder-recurrent neural network machine learning model is presented to analyse and forecast the dynamics and low-order statistics of the local convective heat flux field in a two-dimensional turbulent Rayleigh-B\'{e}nard convection flow at Prandtl number ${\rm Pr}=7$ and Rayleigh number ${\rm Ra}=10^7$.

Synaptic Diversity in ANNs Can Facilitate Faster Learning

no code implementations29 Sep 2021 Martin Hofmann, Moritz F. P. Becker, Christian Tetzlaff, Patrick Mäder

Various advancements in artificial neural networks (ANNs) are inspired by biological concepts, e. g., the artificial neuron, an efficient model of biological nerve cells demonstrating learning capabilities on large amounts of data.

PRECODE - A Generic Model Extension to Prevent Deep Gradient Leakage

1 code implementation10 Aug 2021 Daniel Scheliga, Patrick Mäder, Marco Seeland

We propose a simple yet effective realization of PRECODE using variational modeling.

Cannot find the paper you are looking for? You can Submit a new open access paper.