Responsible AI
Build models that remain reliable under stress
Learning modules
Adversarial Robustness
Uncertainty & Calibration
Fairness & Safety Audits
Secure Deployment
Selected references
- Goodfellow et al., Explaining and Harnessing Adversarial Examples
- Guo et al., On Calibration of Modern Neural Networks
- Barocas, Hardt & Narayanan, Fairness and Machine Learning
- Amodei et al., Concrete Problems in AI Safety