Pramit Chaudhary
Lead data scientist at H2O AI with expertise in model interpretability, AutoML, and tooling for production-scale machine learning, and a former researcher with graduate coursework from UC Irvine.
Best podcasts with Pramit Chaudhary
Ranked by the Snipd community
Mar 13, 2020 • 43min
Interpretability Tooling
Pramit Chaudhary, lead data scientist at H2O AI with expertise in model interpretability and AutoML. He discusses global vs local interpretation and the influence of LIME. He explains SCATER, a unified open source interpretability interface. He covers real-world uses in finance and healthcare, perturbation and robustness testing across text, image, and audio, and integrating interpretability into the model lifecycle.
