训练深度神经网络会自发形成周期性权重结构，与数据无关。
Emergent weight morphologies in deep neural networks
- 用凝聚态物理类比，理论预测权重均匀态不稳定
- 在多个数据集上验证了周期性通道结构的出现
- 揭示了模型性能受限的潜在机制，适合关注模型内在行为的研究者
深度神经网络是否具有涌现行为不仅关乎对深度学习机制的理解，也对评估日益强大的人工智能系统的潜在安全风险至关重要。本文表明，训练深度神经网络会引发与训练数据无关的涌现权重形态。具体而言，类比凝聚态物理，我们推导出理论，预测深度神经网络的均匀状态存在不稳定性，导致周期性通道结构的出现。我们在多种数据集上通过数值实验验证了这些结构。研究证明了深度神经网络训练过程中的涌现现象，该现象影响模型可达到的性能。
原文摘要 · Abstract (English)
Whether deep neural networks can exhibit emergent behaviour is not only relevant for understanding how deep learning works, it is also pivotal for estimating potential security risks of increasingly capable artificial intelligence systems. Here, we show that training deep neural networks gives rise to emergent weight morphologies independent of the training data. Specifically, in analogy to condensed matter physics, we derive a theory that predict that the homogeneous state of deep neural networks is unstable in a way that leads to the emergence of periodic channel structures. We verified these structures by performing numerical experiments on a variety of data sets. Our work demonstrates emergence in the training of deep neural networks, which impacts the achievable performance of deep neural networks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。