Fundamental limits of neural network sparsification: Evidence from catastrophic interpretability collapse
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Fields of Study & Subjects
Explainable Artificial Intelligence (XAI)
Advanced Neural Network Applications
Neural Networks and Applications
Publication details
- Journal / source
- Neurocomputing
- Volume
- 682
- Pages
- 133498–133498
- Publication date
- 27 March 2026
- Language
- EN