Cargando…
Improved Geometric Path Enumeration for Verifying ReLU Neural Networks
Neural networks provide quick approximations to complex functions, and have been increasingly used in perception as well as control tasks. For use in mission-critical and safety-critical applications, however, it is important to be able to analyze what a neural network can and cannot do. For feed-fo...
Autores principales: | Bak, Stanley, Tran, Hoang-Dung, Hobbs, Kerianne, Johnson, Taylor T. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7363204/ http://dx.doi.org/10.1007/978-3-030-53288-8_4 |
Ejemplares similares
-
Integrating geometries of ReLU feedforward neural networks
por: Liu, Yajing, et al.
Publicado: (2023) -
Multimodal transistors as ReLU activation functions in physical neural network classifiers
por: Surekcigil Pesch, Isin, et al.
Publicado: (2022) -
Training a Two-Layer ReLU Network Analytically
por: Barbu, Adrian
Publicado: (2023) -
A Cooperative Lightweight Translation Algorithm Combined with Sparse-ReLU
por: Xu, Xintao, et al.
Publicado: (2022) -
Studying the Evolution of Neural Activation Patterns During Training of Feed-Forward ReLU Networks
por: Hartmann, David, et al.
Publicado: (2021)