Trustworthy Deep Learning

This lecture examines challenges in robust and trustworthy deep learning, including algorithmic bias, imbalanced data, and uncertainty. It introduces DB-VAE debiasing, aleatoric and epistemic uncertainty estimation, evidential deep learning, and risk-aware AI tools.

Syllabus

- Introduction and Themis AI
- Background
- Challenges for Robust Deep Learning
- What is Algorithmic Bias?
- Class imbalance
- Latent feature imbalance
- Debiasing variational autoencoder DB-VAE
- DB-VAE mathematics
- Uncertainty in deep learning
- Types of uncertainty in AI
- Aleatoric vs epistemic uncertainty
- Estimating aleatoric uncertainty
- Estimating epistemic uncertainty
- Evidential deep learning
- Recap of challenges
- How Themis AI is transforming risk-awareness of AI
- Capsa: Open-source risk-aware AI wrapper
- Unlocking the future of trustworthy AI