Responsible AI with SciPy
summary
Shows concrete code and results: bias detection using scipy.stats on the NHANES CKD dataset, a RandomForest model with 0.94 accuracy but heavy class imbalance, and a robustness test that holds under added noise. Reports sensitivity analysis identifying hypertension and age as top drivers, mentions using shap for explainability, cites the Optum error and an 84% bias reduction example, and includes notebooks and partial tutorials (third one unfinished).
AI-written summary · about
chapters (10)
- 0:00Responsible AI with SciPy
- 1:28What is AI and AI systems
- 4:59Responsible AI in healthcare
- 7:47Core principles of responsible AI
- 13:47Best practices for responsible AI
- 16:15SciPy tools for responsible AI
- 17:22Bias detection with SciPy
- 39:11Sensitivity analysis with SciPy
- 47:26Transparent models with SciPy
- 50:26Q&A
related talks
30mReducing Bias in Artificial Intelligence...
30mBias, Explainability, and Accountability: The Data Scientist's Burden
55mEthical Machine Learning
47mFight AI Bias With… Bias
50mEthical Machine Learning
20mResponsible AI in Health
43mThe Elephant in your Dataset: Addressing Bias in Machine Learning
38mResponsible AI In Practice