按年被提到
20192020 · 1 次2026
机器学习与深度学习›深度学习理论与泛化·arXiv:1910.01526 · cs.LG

Gated Linear Networks

Joel Veness, Tor Lattimore, David Budden, Avishkar Bhoopchand, Christopher Mattern, Agnieszka Grabska-Barwinska, Eren Sezener, Jianan Wang, Peter Toth, Simon Schmitt, Marcus Hutter · 2019
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2020-06-15 · 最近 2023-03-26
2不同的人
2活跃月份
2讨论串
7被引(OpenAlex)
arXiv 摘要(候选层不写导读)

This paper presents a new family of backpropagation-free neural architectures, Gated Linear Networks (GLNs). What distinguishes GLNs from contemporary neural networks is the distributed and local nature of their credit assignment mechanism; each neuron directly predicts the target, forgoing the ability to learn feature representations in favor of rapid online learning. Individual neurons can model nonlinear functions via the use of data-dependent gating in conjunction with online convex optimization. We show that this architecture gives rise to universal learning capabilities in the limit, with effective model capacity increasing as a function of network size in a manner comparable with deep ReLU networks. Furthermore, we demonstrate that the GLN learning mechanism possesses extraordinary resilience to catastrophic forgetting, performing comparably to a MLP with dropout and Elastic Weight Consolidation on standard benchmarks. These desirable theoretical and empirical properties position GLNs as a complementary technique to contemporary offline deep learning methods.

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vintermann · 2023-03

“> no one is trying to do statistical inference using compression Well, maybe no one sensible? I still think it's quite cool that you can take any general purpose compression algorithm, and abuse it to do e.g. image classification. (Just append the image you want to classify to each of the classes' sets in turn, and see which compresses best!) And actual…”

Jacob Ziv has died (the Z in LZ compression)原评论 ↗
被提交为 story · 1 次