按年被提到
20172017 · 2 次2026
视觉、语音与图像生成›生成对抗网络·arXiv:1710.09412 · cs.LG

mixup: Beyond Empirical Risk Minimization

Hongyi Zhang, Moustapha Cisse, Yann N. Dauphin, David Lopez-Paz · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-10-31 · 最近 2017-11-08
2不同的人
2活跃月份
2讨论串
5,657被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Large deep neural networks are powerful, but exhibit undesirable behaviors such as memorization and sensitivity to adversarial examples. In this work, we propose mixup, a simple learning principle to alleviate these issues. In essence, mixup trains a neural network on convex combinations of pairs of examples and their labels. By doing so, mixup regularizes the neural network to favor simple linear behavior in-between training examples. Our experiments on the ImageNet-2012, CIFAR-10, CIFAR-100, Google commands and UCI datasets show that mixup improves the generalization of state-of-the-art neural network architectures. We also find that mixup reduces the memorization of corrupt labels, increases the robustness to adversarial examples, and stabilizes the training of generative adversarial networks.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论pinouchon · 2017-11

“Hi. Thanks for the great article. Can you elaborate on what you mean by "directions in activation space" ? If I understand it right: You take a few neurons in a layer, and you follow some linear combination of their weights; you are then walking along a random direction. You take a single neuron and walk along its weights; you walk along this neuron's d…”

Feature Visualization: How neural nets build up their understanding of images原评论 ↗
被提交为 story · 1 次