两篇新研究论文探讨了神经网络批量归一化（BN）的进展。一篇论文研究了训练时BN如何影响分段仿射网络的函数几何分区，并提出它充当了批次条件重置机制。另一篇论文提出了专门用于复杂域上神经网络的BN层，并展示了它们在雷达杂波分类和动作识别等领域的有效性。 AI
影响 这些研究为改善神经网络在复杂数据上的训练稳定性和性能提供了新的理论和实践方法。
排序理由 两篇arXiv论文提出了用于神经网络的批量归一化技术的新颖研究。
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
arXiv:2605.06300v1 Announce Type: new Abstract: Deep networks with continuous piecewise affine activations induce polyhedral partitions of the input space, making the number of realized affine regions a natural measure of expressive capacity and a key determinant of how well the …
arXiv:2605.04946v1 Announce Type: new Abstract: Batch normalization (BN) is central to modern deep networks, but its effect on the realized function during training remains less understood than its optimization benefits. We study training-time BN in continuous piecewise-affine (C…
arXiv:2605.00467v1 Announce Type: new Abstract: Riemannian neural networks have proven effective in solving a variety of machine learning tasks. The key to their success lies in the development of principled Riemannian analogs of fundamental building blocks in deep neural network…
Batch normalization (BN) is central to modern deep networks, but its effect on the realized function during training remains less understood than its optimization benefits. We study training-time BN in continuous piecewise-affine (CPA) networks through the geometry of switching h…
Riemannian neural networks have proven effective in solving a variety of machine learning tasks. The key to their success lies in the development of principled Riemannian analogs of fundamental building blocks in deep neural networks (DNNs). Among those, Riemannian batch normaliz…