按年被提到
20172017 · 1 次2026
机器学习与深度学习›深度学习理论与泛化·arXiv:1706.05394 · stat.ML

A Closer Look at Memorization in Deep Networks

Devansh Arpit, Stanisław Jastrzębski, Nicolas Ballas, David Krueger, Emmanuel Bengio, Maxinder S. Kanwal, Tegan Maharaj, Asja Fischer, Aaron Courville, Yoshua Bengio, Simon Lacoste-Julien · 2017
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2017-06-21 · 最近 2018-02-24
2不同的人
2活跃月份
2讨论串
1,307被引(OpenAlex)
arXiv 摘要(候选层不写导读)

We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While deep networks are capable of memorizing noise data, our results suggest that they tend to prioritize learning simple patterns first. In our experiments, we expose qualitative differences in gradient-based optimization of deep neural networks (DNNs) on noise vs. real data. We also demonstrate that for appropriately tuned explicit regularization (e.g., dropout) we can degrade DNN training performance on noise datasets without compromising generalization on real data. Our analysis suggests that the notions of effective capacity which are dataset independent are unlikely to explain the generalization performance of deep networks when trained with gradient based methods because training data itself plays an important role in determining the degree of memorization.

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fabianhjr · 2018-02

“> Ontology of programs The presuppositions of programs or to program Example: https://arxiv.org/pdf/math/0602053v3.pdf > The epistemological status of computer science Do Neural Nets learn or memorize? What's the difference and how do we know what Neural Nets do? Example: https://arxiv.org/pdf/1706.05394.pdf”

The Philosophy of Computer Science原评论 ↗
被提交为 story · 1 次