Ethical ML: Who’s Afraid of the Black Box Models? • Prayson Daniel • GOTO 2021

This presentation was recorded at GOTO Copenhagen 2021. #GOTOcon #GOTOcph Prayson Daniel - Principal Data Scientist at NTT DATA ABSTRACT Take a dive into the deep depths and pitfalls of explainable machine learning, going beyond the illusions of interpretability and explainability. Draw from Prayson’s experience and explore how ethical data handling and counter-factual fairness model testing help in keeping black-box models and yet satisfy GDPR and ALTAI (Guidelines for Trustworthy AI) [...] TIMECODES 00:00 Intro 01:26 Dragons & unicorns 03:42 Beyond model transparency & explainability 04:30 Why should you care? 07:16 We (data scientists) have messed things up 14:48 We (data scientists) are fixing it 21:25 Demo 33:55 Conclusions 38:34 Outro Read the full abstract here: RECOMMENDED BOOKS Phil Winder • Reinforcement Learning • Kelleher & Tierney • Data Science (The MIT Press Essential Knowl