发表机构
Delft University of Technology; Chalmers University of Technology（代尔夫特理工大学; 查尔姆斯理工大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文研究物理循环神经网络中不同解码器架构对潜在空间可解释性的影响，提出权重归一化约束和伴随编码器-解码器结构，实现低数据下的稳健训练与热力学一致性，提升数据效率。
AI 中文摘要
本文揭示了不同解码器架构对物理循环神经网络潜在空间可解释性的影响。特别强调了一种新的权重归一化约束，该约束作为正则化技术，能够在低数据条件下实现稳健训练。通过简要的可视化探索，展示了这些变化如何影响潜在空间，以及虚构应力如何在没有显式训练的情况下与RVE的真实状态对齐。利用有意义的潜在空间带来的优势，一个案例研究说明了如何从微观层面检索信息并将其纳入多任务方法，而无需额外参数或更大的训练集。另一个关键贡献表明，特定的架构选择可以自然地导致热力学一致性的公式。通过强制具有正标量贡献的伴随编码器-解码器结构，该修改确保了跨尺度的能量一致性和非负耗散，从而进一步降低了训练需求。这一替代方案完善了关于可解释性、归纳偏置和热力学一致性的研究，并证明通过基于底层物理的谨慎架构选择可以提高数据效率。
英文摘要
In this paper, we unravel the effect of different decoder architectures on the interpretability of the latent space of the Physically Recurrent Neural Network. Particular emphasis is given to a new weight normalization constraint, which acts as a regularization technique and enables robust training in the low-data regime. A brief visual exploration illustrates how these changes impact the latent space and how the fictitious stress can align with the true state of the RVE without explicit training. Reaping the benefits of a meaningful latent space, a case study illustrates how information from the microscopic level can be retrieved and incorporated into a multi-task approach that does not require extra parameters or larger training sets. Another key contribution shows that a specific architectural choice can naturally lead to a thermodynamically consistent formulation. By enforcing an adjoint encoder-decoder structure with positive scalar contributions, this modification ensures energy consistency across scales and non-negative dissipation, leading to even lower training requirements. This alternative completes the study on interpretability, inductive bias, and thermodynamic consistency, and demonstrates that data efficiency can be improved with careful architectural choices rooted in the underlying physics.
Comments27 pages, 21 figures
