How to Interpret and Explain Black Box Models

Explore techniques for interpreting and explaining black box machine learning models in this 31-minute conference talk from Data Council. Gain a high-level overview of popular model explanation techniques, including explainable boosting machine, visual analytics, distillation, prototypes, saliency map, counterfactual, feature visualization, LIME, SHAP, interpretML, and TCAV. Learn from Sophia Yang, a Senior Data Scientist and Developer Advocate at Anaconda, as she shares insights on increasing model interpretability and explainability. Discover how these techniques can enhance understanding of complex machine learning models and their decision-making processes. Benefit from Yang's expertise in data science and her contributions to the Python open-source community through various libraries. Expand your knowledge of model interpretation methods to improve transparency and trust in your machine learning projects.

How to Interpret & Explain Your Black Box Models | Anaconda