Minor changes are by default collapsed in the page history.
No changes
The page does not exist yet.
Failed to load changes
Version by on
Leave Collaboration
Are you sure you want to leave the realtime collaboration and continue editing alone? The changes you save while editing alone will lead to merge conflicts with the changes auto-saved by the realtime editing session.
A Comparative Study of Pre-defined and Automatically Discovered Concepts for Interpretability
Valerio Costa • Luca Domeniconi
abstract
The demand for interpretability in Artificial Intelligence (AI) is growing, particularly in high-stakes domains where understanding model decisions is paramount for trust and accountability. This project proposes a comparative study of two distinct approaches to achieving interpretability in computer vi- sion models: Concept Bottleneck Models[Koh+20](CBMs), which leverage human-annotated, pre-defined concepts, and Concept Recursive Activation FacTorization (CRAFT)[Fel+23], which automatically dis- covers concepts from trained neural networks. We aim to explore the strengths and weaknesses of each paradigm in terms of their ability to provide understandable and actionable explanations, and to inves- tigate the semantic alignment between human-engineered concepts and automatically learned concepts. The project will involve implementing and evaluating both methods on a relevant dataset, culminating in a detailed analysis of their interpretability characteristics and ethical implications.
