研究人员推出了 Deep4ge，这是一个新的基准数据集，旨在帮助检测和诊断深度学习系统中的故障。该数据集包含来自 59 个改编的 TensorFlow/Keras 程序的 14,000 多个训练运行，其中包括通过 27 种源代码转换创建的近 10,000 个故障变体。每次运行的特征包括在每个 epoch 测量训练行为的 26 个特征，例如权重、梯度和准确性趋势。Deep4ge 旨在支持二元故障检测、多类故障诊断以及从部分训练数据进行早期故障预测等任务。 AI
影响 提供了一个标准化的数据集，用于提高深度学习模型的可靠性和鲁棒性。
排序理由 该集群包含一篇学术论文，详细介绍了用于深度学习故障检测的新数据集和基准。 [lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.12868v1 Announce Type: cross Abstract: Deep learning systems often fail due to subtle implementation faults that alter training behavior. Recent work has studied how to detect and diagnose such failures from changes observed across training epochs. However, the softwar…
Deep learning systems often fail due to subtle implementation faults that alter training behavior. Recent work has studied how to detect and diagnose such failures from changes observed across training epochs. However, the software engineering community still lacks a public datas…