Distributional shifts are common in real-world problems, e.g. often simulation data is used to train in data-limited domains. Standard neural networks cannot handle such large domain shifts. They also lack uncertainty quantification: they tend to be overconfident when they make errors.  You can read previous posts for other research highlights: generalizable AI (part 1), optimization … Continue reading 2020 AI Research Highlights: Handling distributional shifts (part 2) →
The post 2020 AI Research Highlights: Handling distributional shifts (part 2) first appeared on Anima on AI.

Ver todos los episodios