Obsidian/Zettelkasten/Literature Notes/Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks.md

43 lines
1014 B
Markdown

---
authors:
- "Ehlers, Rüdiger"
- "D'Souza, Deepak"
- "Narayan Kumar, K."
citekey: "ehlersFormalVerificationPieceWise2017"
publish_date: 2017-01-01
publisher: "Springer International Publishing"
location: "Cham"
pages: 269-286
last_import: 2025-05-12
---
# Indexing Information
Published: 2017-01
**DOI**
[10.1007/978-3-319-68167-2_19](https://doi.org/10.1007/978-3-319-68167-2_19)
**ISBN**
[978-3-319-68167-2](https://www.isbnsearch.org/isbn/978-3-319-68167-2)
#ToRead
>[!Abstract]
>We present an approach for the verification of feed-forward neural networks in which all nodes have a piece-wise linear activation function. Such networks are often used in deep learning and have been shown to be hard to verify for modern satisfiability modulo theory (SMT) and integer linear programming (ILP) solvers.>[!seealso] Related Papers
>
# Annotations
## Notes
![[Paper Notes/Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks.md]]
## Highlights From Zotero
## Follow-Ups