Search Results for author:
Found 11 papers, 5 papers with code
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.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Explanations can be manipulated and geometry is to blame
Explanation methods aim to make neural networks more trustworthy and interpretable.
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.
Fairwashing Explanations with Off-Manifold Detergent
Explanation methods promise to make black-box classifiers more transparent.
From Hope to Safety: Unlearning Biases of Deep Models via Gradient Penalization in Latent Space
Deep Neural Networks are prone to learning spurious correlations embedded in the training data, leading to potentially biased predictions.
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.
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.
Towards Robust Explanations for Deep Neural Networks
Explanation methods shed light on the decision process of black-box classifiers such as deep neural networks.
Navigating Neural Space: Revisiting Concept Activation Vectors to Overcome Directional Divergence
With a growing interest in understanding neural network prediction strategies, Concept Activation Vectors (CAVs) have emerged as a popular tool for modeling human-understandable concepts in the latent space.
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.
Towards Fixing Clever-Hans Predictors with Counterfactual Knowledge Distillation
This paper introduces a novel technique called counterfactual knowledge distillation (CFKD) to detect and remove reliance on confounders in deep learning models with the help of human expert feedback.
