1014 B
1014 B
| authors | citekey | publish_date | publisher | location | pages | last_import | |||
|---|---|---|---|---|---|---|---|---|---|
|
ehlersFormalVerificationPieceWise2017 | 2017-01-01 | Springer International Publishing | Cham | 269-286 | 2025-05-12 |
Indexing Information
Published: 2017-01
DOI 10.1007/978-3-319-68167-2_19 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