The troublesome kernel -- On hallucinations, no free lunches and the accuracy-stability trade-off in inverse problems

arXiv:2001.01258v4 Announce Type: replace
Abstract: Methods inspired by Artificial Intelligence (AI) are starting to fundamentally change computational science and engineering through breakthrough performances on challenging problems. However, reliability and trustworthiness of such techniques is a major concern. In inverse problems in imaging, the focus of this paper, there is increasing empirical evidence that methods may suffer from hallucinations, i.e., false, but realistic-looking artifacts; instability, i.e., sensitivity to perturbations in the data; and unpredictable generalization, i.e., excellent performance on some images, …

abstract accuracy artificial artificial intelligence arxiv change computational cs.cv cs.lg engineering focus free hallucinations however imaging intelligence kernel major off performances reliability replace science stability through trade trade-off type