Towards Enhancing the Reproducibility of Deep Learning Bugs: An Empirical Study

arXiv:2401.03069v2 Announce Type: replace-cross
Abstract: Context: Deep learning has achieved remarkable progress in various domains. However, like any software system, deep learning systems contain bugs, some of which can have severe impacts, as evidenced by crashes involving autonomous vehicles. Despite substantial advancements in deep learning techniques, little research has focused on reproducing deep learning bugs, which is an essential step for their resolution. Existing literature suggests that only 3% of deep learning bugs are reproducible, underscoring the need for further …

abstract arxiv autonomous autonomous vehicles bugs context cs.lg cs.se deep learning deep learning techniques domains however impacts learning systems progress replace reproducibility research software study systems type vehicles