Category: Explainability & Interpretability

Attention Rollout

Attention Rollout is a technique used to visualise and interpret how information flows through the layers of an attention-based model, such as a transformer. It helps to track which parts of the input the model focuses on at each stage, giving insight into the decision-making process. This method combines attention maps from different layers to…

Feature Attribution

Feature attribution is a method used in machine learning to determine how much each input feature contributes to a model’s prediction. It helps explain which factors are most important for the model’s decisions, making complex models more transparent. By understanding feature attribution, users can trust and interpret the outcomes of machine learning systems more easily.