In search of inclusive AI
summary
The talk explains how biased training data and unclear definitions of fairness can lead AI systems to produce unjust outcomes (for example, job-search algorithms favoring men or stereotyping women). It surveys the main problems caused by data bias and outlines approaches to build ethical, fair and interpretable machine-learning models.
AI-written summary · about
chapters (13)
- 0:00Welcome and introduction
- 2:27Real bias cases in AI
- 8:05Diversity in dev teams
- 9:29Ethical ML workflow
- 10:10Damage and risk analysis
- 13:00Bias definition and types
- 21:52Data handling and privacy
- 25:03Responsible and transparent models
- 36:27AI model explainability
- 37:49Deployment and continuous monitoring
- 43:03AI laws and regulations
- 46:13AI ethical dilemmas
- 48:44Q&A
related talks
35mIs artificial intelligence "fair"?
40mEthical AI: Addressing Bias & Algorithmic Fairness
21mFairness and bias in AI
56mAn AI with an Agenda: How Our Cognitive Biases Leak Into Machine Learning
26m(Un)ethical Artificial Intelligence: How to Keep the AI Fair for Everyone
11mAddressing Privacy, Bias, and Fairness in AI Systems
36mKeynote: Ethics in AI: Building Fair and Just Intelligence Systems
37mKeynote: Ethical Machine Learning: Creating Fair Models in an Unjust World