Search Results for author:
Found 43 papers, 15 papers with code
Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features
Explainable Artificial Intelligence (XAI) plays a crucial role in fostering transparency and trust in AI systems, where traditional XAI approaches typically offer one level of abstraction for explanations, often in the form of heatmaps highlighting single or multiple input features.
The Clever Hans Effect in Unsupervised Learning
Unsupervised learning has become an essential building block of AI systems.
MambaLRP: Explaining Selective State Space Sequence Models
Recent sequence modeling approaches using selective state space sequence models, referred to as Mamba models, have seen a surge of interest.
XpertAI: uncovering model strategies for sub-manifolds
In regression, explanations need to be precisely formulated to address specific user queries (e. g.\ distinguishing between `Why is the output above 0?'
Explaining Predictive Uncertainty by Exposing Second-Order Effects
So far, the question of explaining predictive uncertainty, i. e. why a model 'doubts', has been scarcely studied.
Insightful analysis of historical sources at scales beyond human capabilities using unsupervised Machine Learning and XAI
An ML based analysis of these tables helps to unveil important facets of the spatio-temporal evolution of knowledge and innovation in the field of mathematical astronomy in the period, as taught at European universities.
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.
Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
In this paper, we demonstrate that acceptance of explanations by the user is not a guarantee for a machine learning model to be robust against Clever Hans effects, which may remain undetected.
Explainable AI for Time Series via Virtual Inspection Layers
In this way, we extend the applicability of a family of XAI methods to domains (e. g. speech) where the input is only interpretable after a transformation.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+3
Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspaces
Explanations often take the form of a heatmap identifying input features (e. g. pixels) that are relevant to the model's decision.
Shortcomings of Top-Down Randomization-Based Sanity Checks for Evaluations of Deep Neural Network Explanations
To address shortcomings of this test, we start by observing an experimental gap in the ranking of explanation methods between randomization-based sanity checks [1] and model output faithfulness measures (e. g. [25]).
XAI for Transformers: Better Explanations through Conservative Propagation
Transformers have become an important workhorse of machine learning, with numerous applications.
Deep learning for surrogate modelling of 2D mantle convection
Using a dataset of 10, 525 two-dimensional simulations of the thermal evolution of the mantle of a Mars-like planet, we show that deep learning techniques can produce reliable parameterized surrogates (i. e. surrogates that predict state variables such as temperature based only on parameters) of the underlying partial differential equations.
Learning Domain Invariant Representations by Joint Wasserstein Distance Minimization
However, common ML losses do not give strong guarantees on how consistently the ML model performs for different domains, in particular, whether the model performs well on a domain at the expense of its performance on another domain.
A Unifying Review of Deep and Shallow Anomaly Detection
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.
GraphKKE: Graph Kernel Koopman Embedding for Human Microbiome Analysis
We demonstrate that our method can capture temporary changes in the time-evolving graph on both created synthetic data and real-world data.
The Clever Hans Effect in Anomaly Detection
The 'Clever Hans' effect occurs when the learned model produces correct predictions based on the 'wrong' features.
Anomaly Detection
Explainable Artificial Intelligence (XAI)
+1
Higher-Order Explanations of Graph Neural Networks via Relevant Walks
In this paper, we show that GNNs can in fact be naturally explained using higher-order expansions, i. e. by identifying groups of edges that jointly contribute to the prediction.
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.
Building and Interpreting Deep Similarity Models
Many learning algorithms such as kernel machines, nearest neighbors, clustering, or anomaly detection, are based on the concept of 'distance' or 'similarity'.
Explaining and Interpreting LSTMs
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 variety of tasks to be solved.
From Clustering to Cluster Explanations via Neural Networks
Cluster predictions of the obtained networks can then be quickly and accurately attributed to the input features.
Unmasking Clever Hans Predictors and Assessing What Machines Really Learn
Current learning machines have successfully solved hard application problems, reaching high accuracy and displaying seemingly "intelligent" behavior.
iNNvestigate neural networks!
The presented library iNNvestigate addresses this by providing a common interface and out-of-the- box implementation for many analysis methods, including the reference implementation for PatternNet and PatternAttribution as well as for LRP-methods.
Unsupervised Detection and Explanation of Latent-class Contextual Anomalies
Detecting and explaining anomalies is a challenging effort.
Understanding Patch-Based Learning by Explaining Predictions
We apply the deep Taylor / LRP technique to understand the deep network's classification decisions, and identify a "border effect": a tendency of the classifier to look mainly at the bordering frames of the input.
Towards Explaining Anomalies: A Deep Taylor Decomposition of One-Class Models
The proposed One-Class DTD is applicable to a number of common distance-based SVM kernels and is able to reliably explain a wide set of data anomalies.
Discovering topics in text datasets by visualizing relevant words
When dealing with large collections of documents, it is imperative to quickly get an overview of the texts' contents.
Exploring text datasets by visualizing relevant words
When working with a new dataset, it is important to first explore and familiarize oneself with it, before applying any advanced machine learning algorithms.
Methods for Interpreting and Understanding Deep Neural Networks
This paper provides an entry point to the problem of interpreting a deep neural network model and explaining its predictions.
Explaining Recurrent Neural Network Predictions in Sentiment Analysis
Recently, a technique called Layer-wise Relevance Propagation (LRP) was shown to deliver insightful explanations in the form of input space relevances for understanding feed-forward neural network classification decisions.
"What is Relevant in a Text Document?": An Interpretable Machine Learning Approach
Text documents can be described by a number of abstract concepts such as semantic category, writing style, or sentiment.
Wasserstein Training of Restricted Boltzmann Machines
This metric between observations can then be used to define the Wasserstein distance between the distribution induced by the Boltzmann machine on the one hand, and that given by the training sample on the other hand.
Interpreting the Predictions of Complex ML Models by Layer-wise Relevance Propagation
Complex nonlinear models such as deep neural network (DNNs) have become an important tool for image classification, speech recognition, natural language processing, and many other fields of application.
Identifying individual facial expressions by deconstructing a neural network
We further observe that the explanation method provides important insights into the nature of features of the base model, which allow one to assess the aptitude of the base model for a given transfer learning task.
Explaining Predictions of Non-Linear Classifiers in NLP
Layer-wise relevance propagation (LRP) is a recently proposed technique for explaining predictions of complex non-linear classifiers in terms of input variables.
Layer-wise Relevance Propagation for Neural Networks with Local Renormalization Layers
Layer-wise relevance propagation is a framework which allows to decompose the prediction of a deep neural network computed over a sample, e. g. an image, down to relevance scores for the single input dimensions of the sample such as subpixels of an image.
Explaining NonLinear Classification Decisions with Deep Taylor Decomposition
Although our focus is on image classification, the method is applicable to a broad set of input data, learning tasks and network architectures.
Analyzing Classifiers: Fisher Vectors and Deep Neural Networks
Fisher Vector classifiers and Deep Neural Networks (DNNs) are popular and successful algorithms for solving image classification problems.
Evaluating the visualization of what a Deep Neural Network has learned
Our main result is that the recently proposed Layer-wise Relevance Propagation (LRP) algorithm qualitatively and quantitatively provides a better explanation of what made a DNN arrive at a particular classification decision than the sensitivity-based approach or the deconvolution method.
Wasserstein Training of Boltzmann Machines
The Boltzmann machine provides a useful framework to learn highly complex, multimodal and multiscale data distributions that occur in the real world.
Learning Invariant Representations of Molecules for Atomization Energy Prediction
The accurate prediction of molecular energetics in chemical compound space is a crucial ingredient for rational compound design.
Layer-wise analysis of deep networks with Gaussian kernels
Deep networks can potentially express a learning problem more efficiently than local learning machines.
