按年被提到
20202020 · 2 次2026
视觉、语音与图像生成›卷积网络与图像识别·arXiv:2007.14745 · eess.IV

On the unreasonable effectiveness of CNNs

Andreas Hauptmann, Jonas Adler · 2020
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2020-07-31 · 最近 2020-08-29
2不同的人
2活跃月份
2讨论串
0被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Deep learning methods using convolutional neural networks (CNN) have been successfully applied to virtually all imaging problems, and particularly in image reconstruction tasks with ill-posed and complicated imaging models. In an attempt to put upper bounds on the capability of baseline CNNs for solving image-to-image problems we applied a widely used standard off-the-shelf network architecture (U-Net) to the "inverse problem" of XOR decryption from noisy data and show acceptable results.

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

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论ipunchghosts · 2020-07

“The authors show that CNNs work well on a problem which, be definition, is discontinuous everywhere!”

On the Unreasonable Effectiveness of CNNs原评论 ↗
被提交为 story · 2 次