Extending Neural Network Verification to a Larger Family of Piece-wise Linear Activation Functions

László Antal, Hana Masara, Erika Ábrahám
11/16/2023
cs.LGcs.AIcs.LO

No confident code implementation found for this paper.

Abstract

In this paper, we extend an available neural network verification technique to support a wider class of piece-wise linear activation functions. Furthermore, we extend the algorithms, which provide in their original form exact respectively over-approximative results for bounded input sets represented as start sets, to allow also unbounded input set. We implemented our algorithms and demonstrated their effectiveness in some case studies.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Robustness Verifcation in Neural Networks

85% match2024

Formalizing Piecewise Affine Activation Functions of Neural Networks in Coq

84% match1 repo62023

Automated Design of Linear Bounding Functions for Sigmoidal Nonlinearities in Neural Networks

83% match2024

Provably Bounding Neural Network Preimages

83% match1 repo92026

Scalable Verification of Neural Control Barrier Functions Using Linear Bound Propagation

82% match2025

Optimal Abstractions for Verifying Properties of Kolmogorov-Arnold Networks (KANs)

81% match1 repo2026

Cite this paper

@article{antal2023extending,
  title  = {Extending Neural Network Verification to a Larger Family of Piece-wise Linear Activation Functions},
  author = {László Antal and Hana Masara and Erika Ábrahám},
  year   = {2023},
  eprint = {2311.10780},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.10780v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.10780.svg)](https://codeofpaper.com/paper/2311.10780)

Discussion