Safety, alignment & interpretability· 2015
On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation
On the reading lists
- #246 in the Top 500 (2026 edition)
- #30 in Safety, alignment & interpretability (2026 edition)
Why it matters
Established relevance propagation as a major alternative to gradient-based neural-network attribution.
Condensed from the expert lists' notes.
Data sources
Catalogue data from OpenAlex (CC0), Crossref (CC0 metadata; no abstracts are shown), arXiv, and Papers With Code (CC BY-SA 4.0). Each count names its source. See the method.