Search Results for author:
Found 11 papers, 7 papers with code
Which LIME should I trust? Concepts, Challenges, and Solutions
As neural networks become dominant in essential systems, Explainable Artificial Intelligence (XAI) plays a crucial role in fostering trust and detecting potential misbehavior of opaque models.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
+2
Decision Trees That Remember: Gradient-Based Learning of Recurrent Decision Trees with Memory
Neural architectures such as Recurrent Neural Networks (RNNs), Transformers, and State-Space Models have shown great success in handling sequential data by learning temporal dependencies.
Aligning Visual and Semantic Interpretability through Visually Grounded Concept Bottleneck Models
We introduce visually Grounded Concept Bottleneck Models (GCBM), which derive concepts on the image level using segmentation and detection foundation models.
Interpreting Outliers in Time Series Data through Decoding Autoencoder
For outlier interpretation, we (i) adopt widely used XAI techniques to the autoencoder's encoder.
Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization
In this paper, we introduce SYMPOL, a novel method for SYMbolic tree-based on-POLicy RL.
A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
Our framework is available under: https://github. com/atschalz/dc_tabeval.
Beyond Pixels: Enhancing LIME with Hierarchical Features and Segmentation Foundation Models
To address these challenges, we introduce the DSEG-LIME (Data-Driven Segmentation LIME) framework, featuring: i) a data-driven segmentation for human-recognized feature generation by foundation model integration, and ii) a user-steered granularity in the hierarchical segmentation procedure through composition.
GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data
Our method combines axis-aligned splits, which is a useful inductive bias for tabular data, with the flexibility of gradient-based optimization.
GradTree: Learning Axis-Aligned Decision Trees with Gradient Descent
Decision Trees (DTs) are commonly used for many machine learning tasks due to their high degree of interpretability.
Explaining Neural Networks without Access to Training Data
We consider generating explanations for neural networks in cases where the network's training data is not accessible, for instance due to privacy or safety issues.
xRAI: Explainable Representations through AI
The approach is based on the idea of training a so-called interpretation network that receives the weights and biases of the trained network as input and outputs the numerical representation of the function the network was supposed to learn that can be directly translated into a symbolic representation.
