Overview
Explore a comprehensive analysis of underspecification in machine learning pipelines through this 59-minute video lecture. Delve into the challenges posed by overparameterized deep learning models and their impact on out-of-distribution performance. Examine real-world examples from computer vision, medical imaging, natural language processing, clinical risk prediction, and medical genomics. Learn about stress tests, theoretical models, and practical applications in epidemiology, ImageNet-C, and BERT models. Gain insights into the importance of addressing underspecification for deploying ML models in real-world domains and understand its implications for model stability and behavior.
Syllabus
- Into & Overview
- Underspecification of ML Pipelines
- Stress Tests
- Epidemiological Example
- Theoretical Model
- Example from Medical Genomics
- ImageNet-C Example
- BERT Models
- Conclusion & Comments
Taught by
Yannic Kilcher