all AI news
Gradient strikes back: How filtering out high frequencies improves explanations
April 1, 2024, 4:43 a.m. | Sabine Muzellec, Thomas Fel, Victor Boutin, L\'eo and\'eol, Rufin VanRullen, Thomas Serre
cs.LG updates on arXiv.org arxiv.org
Abstract: Attribution methods correspond to a class of explainability methods (XAI) that aim to assess how individual inputs contribute to a model's decision-making process. We have identified a significant limitation in one type of attribution methods, known as "white-box" methods. Although highly efficient, these methods rely on a gradient signal that is often contaminated by high-frequency noise. To overcome this limitation, we introduce a new approach called "FORGrad". This simple method effectively filters out noise artifacts …
abstract aim arxiv attribution box class cs.ai cs.cv cs.lg decision explainability filtering gradient inputs making process strikes type xai
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Business Data Analyst
@ Alstom | Johannesburg, GT, ZA