LGAILONov 16, 2023

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

arXiv:2311.10780v1h-index: 3
Originality Synthesis-oriented
AI Analysis

This work addresses verification challenges for neural networks with diverse activation functions, but it is incremental as it builds on prior methods.

The paper extends an existing neural network verification technique to support a wider class of piece-wise linear activation functions and unbounded input sets, demonstrating effectiveness in case studies.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes