Search Results for author:
Found 9 papers, 4 papers with code
Detecting and Mitigating Mode-Collapse for Flow-based Sampling of Lattice Field Theories
In this work, we first point out that the tunneling problem is also present for normalizing flows but is shifted from the sampling to the training phase of the algorithm.
PatClArC: Using Pattern Concept Activation Vectors for Noise-Robust Model Debugging
We demonstrate that pattern-based artifact modeling has beneficial effects on the application of CAVs as a means to remove influence of confounding features from models via the ClArC framework.
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 prediction strategies can rarely be understood.
Towards Robust Explanations for Deep Neural Networks
Explanation methods shed light on the decision process of black-box classifiers such as deep neural networks.
Fairwashing Explanations with Off-Manifold Detergent
Explanation methods promise to make black-box classifiers more transparent.
Estimation of Thermodynamic Observables in Lattice Field Theories with Deep Generative Models
In this work, we demonstrate that applying deep generative machine learning models for lattice field theory is a promising route for solving problems where Markov Chain Monte Carlo (MCMC) methods are problematic.
Explaining Deep Neural Networks and Beyond: A Review of Methods and Applications
With the broader and highly successful usage of machine learning in industry and the sciences, there has been a growing demand for Explainable AI.
Finding and Removing Clever Hans: Using Explanation Methods to Debug and Improve Deep Models
Based on a recent technique - Spectral Relevance Analysis - we propose the following technical contributions and resulting findings: (a) a scalable quantification of artifactual and poisoned classes where the machine learning models under study exhibit CH behavior, (b) several approaches denoted as Class Artifact Compensation (ClArC), which are able to effectively and significantly reduce a model's CH behavior.
Explanations can be manipulated and geometry is to blame
Explanation methods aim to make neural networks more trustworthy and interpretable.
