Search Results for author:
Found 5 papers, 2 papers with code
When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReX
It explains the predictive behavior of a model on a set of images by masking (ir-)relevant concepts from the decision-making process and by constraining relations in a learned interpretable surrogate model.
Generating Contrastive Explanations for Inductive Logic Programming Based on a Near Miss Approach
Such near misses have been proposed by Winston (1970) as efficient guidance for learning in relational domains.
Expressive Explanations of DNNs by Combining Concept Analysis with ILP
We show that our explanation is faithful to the original black-box model.
Effect of Superpixel Aggregation on Explanations in LIME -- A Case Study with Biological Data
Quick-Shift resulted in the least and Compact-Watershed in the highest correspondence with the reference relevance areas.
Enriching Visual with Verbal Explanations for Relational Concepts -- Combining LIME with Aleph
First, we show that our approach is capable of identifying a single relation as important explanatory construct.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
