FIELD NOTES TOPIC
xai
3 notes, newest first.
Entropy-Centric Explainable AI for Remote Sensing Image Segmentation
The provided text discusses a new Explainable AI (XAI) method for semantic image segmentation in remote sensing, which aims to increase transparency and trust in AI models. The proposed method is based on entropy and…
Rule of Thumb: Explaining Artificial Intelligence Systems using Partial Information
Researchers propose a new approach called 'Rule of Thumb' (RoT) explanations for Explainable Artificial Intelligence (XAI). This method identifies the most relevant features that influence an AI system's behavior for a…
Challenges in Evaluating Explanation Methods for Static and Evolving Data
This research paper highlights the issues in evaluating Explanation Methods for AI systems, using the DetoxAI image recognition system as an example. It discusses methods for adapting explanations to changing data…
