2.8k citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Technische Universität BerlinDE80 papers
- Freie Universität BerlinDE40 papers
- Helmholtz-Zentrum Berlin für Materialien und EnergieDE27 papers
- Humboldt-Universität zu BerlinDE23 papers
- Korea UniversityKR15 papers
- Commissariat à l'Énergie Atomique et aux Énergies AlternativesFR13 papers
- Max Planck Institute for InformaticsDE11 papers
- Berlin Institute for the Foundations of Learning and DataDE9 papers
- Fraunhofer-GesellschaftDE9 papers
- Macedonian Academy of Sciences and ArtsMK9 papers
- Singapore University of Technology and DesignSG9 papers
- Technical University of MunichDE9 papers
30 papers · 1 filter
Leveraging Influence Functions for Resampling Data in Physics-Informed Neural Networks
Jonas R. Naujoks, Aleksander Krasowski, Moritz Weckbecker +5
Physics-informed neural networks (PINNs) offer a powerful approach to solving partial differential equations (PDEs), which are ubiquitous in the quantitative sciences. Applied to b…
Optimizing Learned Image Compression on Scalar and Entropy-Constraint Quantization
Florian Borzechowski, Michael Schäfer, Heiko Schwarz +3
The continuous improvements on image compression with variational autoencoders have lead to learned codecs competitive with conventional approaches in terms of rate-distortion effi…
FADE: Why Bad Descriptions Happen to Good Features
Bruno Puri, Aakriti Jain, Elena Golimblevskaia +4
Recent advances in mechanistic interpretability have highlighted the potential of automating interpretability pipelines in analyzing the latent representations within LLMs. While t…
The Clever Hans Effect in Unsupervised Learning
Jacob Kauffmann, Jonas Dippel, Lukas Ruff +3
Unsupervised learning has become an essential building block of AI systems. The representations it produces, e.g. in foundation models, are critical to a wide variety of downstream…
Explaining Predictive Uncertainty by Exposing Second-Order Effects
Florian Bley, Sebastian Lapuschkin, Wojciech Samek +1
Explainable AI has brought transparency into complex ML blackboxes, enabling, in particular, to identify which features these models use for their predictions. So far, the question…
Insights Into the Inner Workings of Transformer Models for Protein Function Prediction
Markus Wenzel, Erik Grüner, Nils Strodthoff
Motivation: We explored how explainable artificial intelligence (XAI) can help to shed light into the inner workings of neural networks for protein function prediction, by extendin…
Bridging the Gap: Gaze Events as Interpretable Concepts to Explain Deep Neural Sequence Models
Daniel G. Krakowczyk, Paul Prasse, David R. Reich +3
Recent work in XAI for eye tracking data has evaluated the suitability of feature attribution methods to explain the output of deep neural sequence models for the task of oculomotr…
Berlin V2X: A Machine Learning Dataset from Multiple Vehicles and Radio Access Technologies
Rodrigo Hernangómez, Philipp Geuer, Alexandros Palaios +14
The evolution of wireless communications into 6G and beyond is expected to rely on new machine learning (ML)-based capabilities. These can enable proactive decisions and actions fr…
Explaining machine learning models for age classification in human gait analysis
Djordje Slijepcevic, Fabian Horst, Marvin Simak +7
Machine learning (ML) models have proven effective in classifying gait analysis data, e.g., binary classification of young vs. older adults. ML models, however, lack in providing h…
Explaining automated gender classification of human gait
Fabian Horst, Djordje Slijepcevic, Matthias Zeppelzauer +6
State-of-the-art machine learning (ML) models are highly effective in classifying gait analysis data, however, they lack in providing explanations for their predictions. This "blac…
The secret role of undesired physical effects in accurate shape sensing with eccentric FBGs
Samaneh Manavi Roodsari, Sara Freund, Martin Angelmahr +3
Fiber optic shape sensors have enabled unique advances in various navigation tasks, from medical tool tracking to industrial applications. Eccentric fiber Bragg gratings (FBG) are…
From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagation
Reduan Achtibat, Maximilian Dreyer, Ilona Eisenbraun +4
The field of eXplainable Artificial Intelligence (XAI) aims to bring transparency to today's powerful but opaque deep learning models. While local XAI methods explain individual pr…
Toward Explainable AI for Regression Models
Simon Letzgus, Patrick Wagner, Jonas Lederer +3
In addition to the impressive predictive power of machine learning (ML) models, more recently, explanation methods have emerged that enable an interpretation of complex non-linear…
ECQ: Explainability-Driven Quantization for Low-Bit and Sparse DNNs
Daniel Becking, Maximilian Dreyer, Wojciech Samek +2
The remarkable success of deep neural networks (DNNs) in various applications is accompanied by a significant increase in network parameters and arithmetic operations. Such increas…
PredDiff: Explanations and Interactions from Conditional Expectations
Stefan Blücher, Johanna Vielhaben, Nils Strodthoff
PredDiff is a model-agnostic, local attribution method that is firmly rooted in probability theory. Its simple intuition is to measure prediction changes while marginalizing featur…
A Unifying Review of Deep and Shallow Anomaly Detection
Lukas Ruff, Jacob R. Kauffmann, Robert A. Vandermeulen +5
Deep learning approaches to anomaly detection have recently improved the state of the art in detection performance on complex datasets such as large collections of images or text.…
Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T)
Arturo Marban, Daniel Becking, Simon Wiedemann +1
Deep neural networks (DNN) have shown remarkable success in a variety of machine learning applications. The capacity of these models (i.e., number of parameters), endows them with…
Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training
Simon Wiedemann, Temesgen Mehari, Kevin Kepp +1
Deep Neural Networks are successful but highly computationally expensive learning systems. One of the main sources of time and energy drains is the well known backpropagation (back…
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
Wojciech Samek, Grégoire Montavon, Sebastian Lapuschkin +2
With the broader and highly successful usage of machine learning in industry and the sciences, there has been a growing demand for Explainable AI. Interpretability and explanation…
Pruning by Explaining: A Novel Criterion for Deep Neural Network Pruning
Seul-Ki Yeom, Philipp Seegerer, Sebastian Lapuschkin +4
The success of convolutional neural networks (CNNs) in various applications is accompanied by a significant increase in computation and parameter storage costs. Recent efforts to r…
On the Explanation of Machine Learning Predictions in Clinical Gait Analysis
Djordje Slijepcevic, Fabian Horst, Sebastian Lapuschkin +6
Machine learning (ML) is increasingly used to support decision-making in the healthcare sector. While ML approaches provide promising results with regard to their classification pe…
Explaining and Interpreting LSTMs
Leila Arras, Jose A. Arjona-Medina, Michael Widrich +5
While neural networks have acted as a strong unifying force in the design of modern AI systems, the neural network architectures themselves remain highly heterogeneous due to the v…
DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
Simon Wiedemann, Heiner Kirchoffer, Stefan Matlage +10
The field of video compression has developed some of the most sophisticated and efficient compression algorithms known in the literature, enabling very high compressibility for lit…
From Clustering to Cluster Explanations via Neural Networks
Jacob Kauffmann, Malte Esders, Lukas Ruff +3
A recent trend in machine learning has been to enrich learned models with the ability to explain their own predictions. The emerging field of Explainable AI (XAI) has so far mainly…