Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Responsible ML

Responsible ML

This is a 30 minutes presentation I did for Global AI Nights Istanbul where I introduced the concept of Responsible ML and talked about projects such as Fairlearn, InterpretML, and SmartNoise.

Daron Yondem

April 24, 2021
Tweet

More Decks by Daron Yondem

Other Decks in Technology

Transcript

  1. The What and the Why? • Fairness: ML models may

    behave unfairly by negatively impacting groups of people, such as those defined in terms of race, gender, or age. • Interpretability: Ability to explain what parameters are used and how the models “think” to explain the outcome for regulatory oversight. • Differential Privacy: Monitoring applications’ use of personal data without accessing or knowing the identities of individuals
  2. Fairlearn • Fairness Assessment • Fairness Mitigation (in Classification and

    Regression Models) • During or after model building. • Open Source https://github.com/fairlearn • Integrated into Azure Machine Learning
  3. InterpretML • Glassbox Models (Decision trees, rule lists, linear models,

    Explainable Boosting Machine) • Blackbox Models (Existing model) • Explanations are approximations • Open Source https://github.com/interpretml
  4. Differential Privacy The guarantee of a differentially private algorithm is

    that its behavior hardly changes when a single individual joins or leaves the dataset. • Smart Noise https://smartnoise.org/ This toolkit uses state-of-the-art differential privacy (DP) techniques to inject noise into data, to prevent disclosure of sensitive information and manage exposure risk.
  5. Links worth sharing Microsoft Learn : Explore differential privacy •

    https://drn.fyi/2QRL3V1 Capgemini “AI and the ethical conundrum” Report • https://drn.fyi/3gBsz5G IDC report: Empowering your organization with Responsible AI • https://drn.fyi/3sKilCx