Gaussian Perturbations in ReLU Networks and the Arrangement of Activation Regions
Recent articles indicate that deep neural networks are efficient models for various learning problems. However, they are often highly sensitive to various changes that cannot be detected by an independent observer. As our understanding of deep neural networks with traditional generalisation bounds s...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI
2022
|
| Subjects: | |
| Online Access: | View Fulltext in Publisher |