activity
20232026
most citedExtending Neural Network Verification to a Larger Family of Piece-wise Linear Activation Functions

4 citations · 4 across the 2 of their papers we have counts for

collaborators
Showing 2026Show all

1 paper · 1 filter

cs.LG2026

Shifting-based Optimizable Linear Relaxations for General Activation Functions

Philipp Kern, László Antal, Erika Ábráham +1

The use of neural networks (NNs) is rapidly increasing, including in safety- and security-critical domains. To provide formal guarantees about NN behavior, many verification method…