最小化ReLU网络的神经元数量被证明是NP难问题

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-09 04:00

一篇新发表在arXiv上的论文表明，确定一个具有两个隐藏层的ReLU神经网络逼近目标函数所需的最小神经元数量是一个NP难问题。这一发现对于各种逼近约束甚至简化的网络架构都成立。研究表明，优化ReLU神经网络可能需要启发式方法，因为在多项式时间内实现最优配置是计算上不可行的。 AI

影响理论发现表明，优化神经网络架构需要启发式方法，这将影响未来在高效模型设计方面的研究。

排序理由详细介绍神经网络架构理论计算复杂性的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍神经网络架构理论计算复杂性的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

arXiv cs.LG TIER_1 English(EN) · Sangrock Lee · 2026-10-09 04:00

NP-Hardness of Minimizing Neurons in Two-Hidden-Layer ReLU Neural Networks

arXiv:2610.11313v1 Announce Type: new Abstract: A fundamental question in neural network architecture optimization is whether the minimum hidden-neuron count required to approximate a target function within a prescribed tolerance can be computed efficiently. This paper resolves t…