按年被提到
20262026 · 2 次2026
机器学习与深度学习›神经网络架构探索·arXiv:2605.04325 · cs.LG

On the Architectural Complexity of Neural Networks

Nicholas J. Cooper, François G. Meyer, Michael L. Roberts, Carlos Zapata-Carratalá, Lijun Chen, Danna Gurari · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-06-16 · 最近 2026-09-28
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)

We introduce a unified theoretical framework for the rigorous analysis and systematic construction of deep neural networks (DNNs). This framework addresses a gap in existing theory by explicitly modeling the structure of tensor operations -- lower level information that is often abstracted. Our framework enables two novel objectives: (1) analysis of the evolution of architectural complexity over deep learning history, and (2) automatic construction of novel architectures based on new types of tensor operations. Our study of DNNs introduced over the past 40 years reveals a connection between groundbreaking architectures and increases in different types of architectural complexity. Moreover, we identify several large classes of higher complexity architectures that have not yet been explored. We then collect a dataset of 3,000+ higher complexity architectures, which we publicly release at: https://github.com/combinatoriallabs/ArchitecturalComplexity.

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combilabs · 2026-09

“Several weeks ago, we published a more substantive article using this very same analogy: https://www.linkedin.com/pulse/announcing-universal-mathematical-framework-deep-lnldc/?trackingId=HyNgLUhqtweh5aCmE53VMw%3D%3D The article describes a unifying mathematical framework for representing neural network architectures. It can be used to describe existing …”

Cambrian Explosion of AI原评论 ↗
被提交为 story · 1 次