MLDS 2019: Indranath Mukherjee of AXA XL at Machine Learning Developers Summit 2019
summary
Explains methods for making machine learning models interpretable in enterprise settings, focusing on techniques for model explanation and their application to insurance/analytics use cases. Mentions concrete approaches to explaining model decisions (post-hoc explanation methods and model-agnostic techniques) and discusses practical considerations for deploying explainability in production.
AI-written summary · about
related talks
46mExplaining a Machine Learning blackbox
29mTowards Explainable Machine Learning
30mKeep Calm and Trust your Model - On Explainability of Machine Learning Models
17mChallenges Towards Production-Ready Explainable Machine Learning
47mML: Explainable Artificial Intelligence explained
24mWhy and How to Build Explainability into your ML Workflow
28mExplaining Machine Learning Models with LLMs
39mGuide towards algorithm explainability in machine learning