Adversarial robustness of Bayesian neural networks
<p>This thesis puts forward methods for computing local robustness of probabilistic neural networks, specifically those resulting from Bayesian inference. In theory, applying Bayesian inference to the learning of neural network parameters carries the promise of solving many practically vexing...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Language: | English |
| Published: |
2021
|
| Subjects: |