Interpretability in Deep Learning
Date:
This talk focuses on the importance and methods of making machine learning models, particularly deep learning models, interpretable and understandable. Computation and search has eliminated the need for domain-specific feature engineering. However, this has a caveat - deep models often behave like black boxes, and are prone to issues of trust, transparency, and safety, especially in mission-critical applications.
Target audience: Freshman year undergraduates.
Slides: PDF
Colab notebook: Link