按年被提到
20152015 · 2 次2026
视觉、语音与图像生成›ViT 与视觉新架构·arXiv:1506.03767 · stat.ML

Spectral Representations for Convolutional Neural Networks

Oren Rippel, Jasper Snoek, Ryan P. Adams · 2015
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2015-06-12 · 最近 2015-12-23
2不同的人
2活跃月份
2讨论串
276被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Discrete Fourier transforms provide a significant speedup in the computation of convolutions in deep learning. In this work, we demonstrate that, beyond its advantages for efficient computation, the spectral domain also provides a powerful representation in which to model and train convolutional neural networks (CNNs). We employ spectral representations to introduce a number of innovations to CNN design. First, we propose spectral pooling, which performs dimensionality reduction by truncating the representation in the frequency domain. This approach preserves considerably more information per parameter than other pooling strategies and enables flexibility in the choice of pooling output dimensionality. This representation also enables a new form of stochastic regularization by randomized modification of resolution. We show that these methods achieve competitive results on classification and approximation tasks, without using any dropout or max-pooling. Finally, we demonstrate the effectiveness of complex-coefficient spectral parameterization of convolutional filters. While this leaves the underlying model unchanged, it results in a representation that greatly facilitates optimization. We observe on a variety of popular CNN configurations that this leads to significantly faster convergence during training.

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nrmn · 2015-12

“I've been trying to read a paper a day since midsummer. These are a few of the interesting, for me personally, since then: Generating Sequences With Recurrent Neural Networks - http://arxiv.org/abs/1308.0850 Older one, but important to understand deeply since other recent ideas have come from this! Unsupervised Representation Learning with Deep Convolu…”

Ask HN: Papers you read in 2015?原评论 ↗
被提交为 story · 1 次