2.4.3 Debugging ML Models and Pipelines

Course subject(s) Module 2. Crowdsourcing for AI

In previous lectures, we discussed how humans can be used to explain what a model is doing. Instead, in this lecture, we focus on defining failure cases of machine learning models and the importance of defining the expected model behaviour. Finally, we shift our attention to ML pipelines and discuss the challenges in debugging them.

Debugging ML Models and Pipelines

Creative Commons License
AI skills for engineers: Data creation and collection by TU Delft OpenCourseWare is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Based on a work at https://online-learning.tudelft.nl/courses/data-creation-and-collection-for-artificial-intelligence-via-crowdsourcing/ /
Back to top