research
∙
07/05/2023
Set Learning for Accurate and Calibrated Models
Model overconfidence and poor calibration are common in machine learning...
share
research
∙
04/19/2023
Towards transparent and robust data-driven wind turbine power curve models
Wind turbine power curve models translate ambient conditions into turbin...
research
∙
04/12/2023
Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
Explainable AI has become a popular tool for validating machine learning...
research
∙
03/09/2023
Mark My Words: Dangers of Watermarked Images in ImageNet
The utilization of pre-trained networks, especially those trained on Ima...
research
∙
12/30/2022
Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
Explainable AI transforms opaque decision strategies of ML models into e...
research
∙
12/24/2022
Reconstructing Kernel-based Machine Learning Force Fields with Super-linear Convergence
Kernel machines have sustained continuous progress in the field of quant...
research
∙
11/22/2022
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
While the evaluation of explanations is an important step towards trustw...
research
∙
08/25/2022
Algorithmic Differentiation for Automatized Modelling of Machine Learned Force Fields
Reconstructing force fields (FF) from atomistic simulation data is a cha...
research
∙
06/10/2022
Diffeomorphic Counterfactuals with Generative Models
Counterfactuals can explain classification decisions of neural networks ...
research
∙
06/09/2022
DORA: Exploring outlier representations in Deep Neural Networks
Deep Neural Networks (DNNs) draw their power from the representations th...
research
∙
05/28/2022
So3krates – Self-attention for higher-order geometric interactions on arbitrary length-scales
The application of machine learning methods in quantum chemistry has ena...
research
∙
05/23/2022
Exposing Outlier Exposure: What Can Be Learned From Few, One, and Zero Outlier Images
Traditionally anomaly detection (AD) is treated as an unsupervised probl...
research
∙
05/17/2022
Accurate Machine Learned Quantum-Mechanical Force Fields for Biomolecular Simulations
Molecular dynamics (MD) simulations allow atomistic insights into chemic...
research
∙
03/30/2022
Automatic Identification of Chemical Moieties
In recent years, the prediction of quantum mechanical observables with m...
research
∙
02/15/2022
XAI for Transformers: Better Explanations through Conservative Propagation
Transformers have become an important workhorse of machine learning, wit...
research
∙
01/07/2022
Automated Dissipation Control for Turbulence Simulation with Shell Models
The application of machine learning (ML) techniques, especially neural n...
research
∙
01/02/2022
Super-resolution in Molecular Dynamics Trajectory Reconstruction with Bi-Directional Neural Networks
Molecular dynamics simulations are a cornerstone in science, allowing to...
research
∙
12/21/2021
Toward Explainable AI for Regression Models
In addition to the impressive predictive power of machine learning (ML) ...
research
∙
11/14/2021
Scrutinizing XAI using linear ground-truth data with suppressor variables
Machine learning (ML) is increasingly often used to inform high-stakes d...
research
∙
11/02/2021
Efficient Hierarchical Bayesian Inference for Spatio-temporal Regression Models in Neuroimaging
Several problems in neuroimaging and beyond require inference on the par...
research
∙
11/01/2021
Evaluating deep transfer learning for whole-brain cognitive decoding
Research in many fields has shown that transfer learning (TL) is well-su...
research
∙
09/10/2021
Inverse design of 3d molecular structures with conditional generative neural networks
The rational design of molecules with desired properties is a long-stand...
research
∙
08/23/2021
Explaining Bayesian Neural Networks
To make advanced learning machines such as Deep Neural Networks (DNNs) m...
research
∙
06/25/2021
On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy
There is an increasing number of medical use-cases where classification ...
research
∙
06/24/2021
Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAy
Deep Neural Networks (DNNs) are known to be strong predictors, but their...
research
∙
06/09/2021
Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization
Domain shifts in the training data are common in practical applications ...
research
∙
06/08/2021
BIGDML: Towards Exact Machine Learning Force Fields for Materials
Machine-learning force fields (MLFF) should be accurate, computationally...
research
∙
06/04/2021
SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
Machine learning has enabled the prediction of quantum chemical properti...
research
∙
05/25/2021
Optimal Sampling Density for Nonparametric Regression
We propose a novel active learning strategy for regression, which is mod...
research
∙
05/01/2021
SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
In recent years, machine-learned force fields (ML-FFs) have gained incre...
research
∙
12/18/2020
Towards Robust Explanations for Deep Neural Networks
Explanation methods shed light on the decision process of black-box clas...
research
∙
10/28/2020
Machine learning of solvent effects on molecular spectra and reactions
Fast and accurate simulation of complex chemical systems in environments...
research
∙
10/14/2020
Machine Learning Force Fields
In recent years, the use of Machine Learning (ML) in computational chemi...
research
∙
09/24/2020
A Unifying Review of Deep and Shallow Anomaly Detection
Deep learning approaches to anomaly detection have recently improved the...
research
∙
08/31/2020
Langevin Cooling for Domain Translation
Domain translation is the task of finding correspondence between two dom...
research
∙
07/20/2020
Fairwashing Explanations with Off-Manifold Detergent
Explanation methods promise to make black-box classifiers more transpare...
research
∙
07/03/2020
Explainable Deep One-Class Classification
Deep one-class classification variants for anomaly detection learn a map...
research
∙
06/18/2020
The Clever Hans Effect in Anomaly Detection
The 'Clever Hans' effect occurs when the learned model produces correct ...
research
∙
06/16/2020
How Much Can I Trust You? – Quantifying Uncertainties in Explaining Neural Networks
Explainable AI (XAI) aims to provide interpretations for predictions mad...
research
∙
06/05/2020
XAI for Graphs: Explaining Graph Neural Network Predictions by Identifying Relevant Walks
Graph Neural Networks (GNNs) are a popular approach for predicting graph...
research
∙
05/30/2020
Rethinking Assumptions in Deep Anomaly Detection
Though anomaly detection (AD) can be viewed as a classification problem ...
research
∙
05/04/2020
Ensemble Learning of Coarse-Grained Molecular Dynamics Force Fields with a Kernel Approach
Gradient-domain machine learning (GDML) is an accurate and efficient app...
research
∙
04/22/2020
Risk Estimation of SARS-CoV-2 Transmission from Bluetooth Low Energy Measurements
Digital contact tracing approaches based on Bluetooth low energy (BLE) h...
research
∙
03/20/2020
Automatic Identification of Types of Alterations in Historical Manuscripts
Alterations in historical manuscripts such as letters represent a promis...
research
∙
03/17/2020
Toward Interpretable Machine Learning: Transparent Deep Neural Networks and Beyond
With the broader and highly successful usage of machine learning in indu...
research
∙
03/11/2020
Building and Interpreting Deep Similarity Models
Many learning algorithms such as kernel machines, nearest neighbors, clu...
research
∙
02/27/2020
Autonomous robotic nanofabrication with reinforcement learning
The ability to handle single molecules as effectively as macroscopic bui...
research
∙
02/05/2020
Forecasting Industrial Aging Processes with Machine Learning Methods
By accurately predicting industrial aging processes (IAPs), it is possib...
research
∙
12/22/2019
Analyzing ImageNet with Spectral Relevance Analysis: Towards ImageNet un-Hans'ed
Today's machine learning models for computer vision are typically traine...
research
∙
12/18/2019