PulseAugur
中
实时 05:27:56
English(EN) Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization

新的NOTES方法增强了物理系统的逆向设计

作者 PulseAugur 编辑部 · [3 个来源] ·

研究人员开发了一种名为神经算子驱动的拓扑感知演化策略（NOTES）的新方法，以改进由偏微分方程控制的物理系统的逆向设计。该方法结合了DeepONet神经算子和协方差矩阵自适应演化策略（CMA-ES），以降低设计维度并提高效率。NOTES应用于纳米光子束偏转器和结构优化，与现有方法相比表现出优越的性能，实现了高效率和改进的顺应性。 AI

影响 这项研究为设计复杂的物理系统提供了一个更高效、更具可转移性的框架，有望加速纳米光子学和结构工程等领域的创新。

排序理由 该集群描述了在arXiv上的一篇学术论文中提出的一种新方法。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →

新的NOTES方法增强了物理系统的逆向设计

报道来源 [3]

  1. arXiv cs.LG TIER_1 English(EN) · Xiangming Huang, Guannan Zhang, Lu Lu, Rapha\"el Pestourie ·

    Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization

    arXiv:2607.07682v1 Announce Type: new Abstract: The inverse design of physical systems governed by partial differential equations is computationally demanding due to the high dimensionality and non-convexity of design spaces. Generative models for inverse design often lack robust…

  2. arXiv cs.LG TIER_1 English(EN) · Raphaël Pestourie ·

    Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization

    The inverse design of physical systems governed by partial differential equations is computationally demanding due to the high dimensionality and non-convexity of design spaces. Generative models for inverse design often lack robustness and transferability, whereas evolutionary s…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

    Neural Operator-enabled Topology-informed Evolutionary Strategy for PDE-Constrained Optimization

    The inverse design of physical systems governed by partial differential equations is computationally demanding due to the high dimensionality and non-convexity of design spaces. Generative models for inverse design often lack robustness and transferability, whereas evolutionary s…

相关实体

相关话题