Jefferson Building, Room 450, 17 Oxford Street, Cambridge, MA 02138
Instructors
Bret Nestor and Claudio Battiloro
Learning Outcomes
- AI ethical frameworks (virtue, rights-based, care-based, utilitarian, deontology). AI regulations. Impact of AI on the labor market.
- How to make a machine learning model safe for sharing
- Measuring bias in a dataset, correcting bias in a dataset
- Privacy protection.
Use Cases
- Discussion on AI ethics, AI Regulations in the US and EU, AI impact on the labor market and society. Academic integrity
- guidelines. [50%]
- Hands-on Session on [50%]:
- IRB-approved privacy/cell suppression
- How a linkage attack works
- Model bias and fairness
- Safe-for-publication/Safe-for-prompting data summary with diļ¬erential privacy
- Safety/Safe prompting
Prerequisites
- Python programming with familiarity in Pytorch
- Basic understanding of neural networks
- GPU access (e.g., free-tier Google Colab)