Teaching Uncertainty Quantification in Machine Learning through Use Cases
This addresses the problem of inadequate teaching of uncertainty concepts for machine learning students and educators, but it is incremental as it builds on existing educational methods.
The authors tackled the lack of uncertainty quantification education in machine learning curricula by proposing a short course with use cases covering output uncertainty, Bayesian neural networks, and out-of-distribution detection, aiming to motivate adoption for AI safety.
Uncertainty in machine learning is not generally taught as general knowledge in Machine Learning course curricula. In this paper we propose a short curriculum for a course about uncertainty in machine learning, and complement the course with a selection of use cases, aimed to trigger discussion and let students play with the concepts of uncertainty in a programming setting. Our use cases cover the concept of output uncertainty, Bayesian neural networks and weight distributions, sources of uncertainty, and out of distribution detection. We expect that this curriculum and set of use cases motivates the community to adopt these important concepts into courses for safety in AI.