Search Results for author:
Found 10 papers, 4 papers with code
DSEG-LIME -- Improving Image Explanation by Hierarchical Data-Driven Segmentation
Explainable Artificial Intelligence is critical in unraveling decision-making processes in complex machine learning models.
A Mechanistic Analysis of a Transformer Trained on a Symbolic Multi-Step Reasoning Task
We anticipate that the motifs we identified in our synthetic setting can provide valuable insights into the broader operating principles of transformers and thus provide a basis for understanding more complex models.
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.
A Multidimensional Analysis of Social Biases in Vision Transformers
Therefore, we measure the impact of training data, model architecture, and training objectives on social biases in the learned representations of ViTs.
Planning Landmark Based Goal Recognition Revisited: Does Using Initial State Landmarks Make Sense?
In this paper, we show that it does not provide any benefit to use landmarks that are part of the initial state in a planning landmark based goal recognition approach.
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.
Leveraging Planning Landmarks for Hybrid Online Goal Recognition
Furthermore, we show that the utilized planning landmark based approach, which was so far only evaluated on artificial benchmark domains, achieves also good recognition performance when applied to a real-world cooking scenario.
Outlier Explanation via Sum-Product Networks
Existing methods are based on beam search in the space of feature subsets.
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.
Exchangeability-Aware Sum-Product Networks
On the other hand, mixtures of exchangeable variable models (MEVMs) are a class of tractable probabilistic models that make use of exchangeability of discrete random variables to render inference tractable.
