arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.01060cs.LG
收藏

热力学信息神经网络的单生成元与双生成元形式化比较

A comparison of Single- and Double-generator formalisms for Thermodynamics-Informed Neural Networks

ESI Group(ESI集团);Aragon Institute of Engineering Research (I3A)(阿拉贡工程研究所);Universidad de Zaragoza(萨拉戈萨大学);ENSAM Arts et Métiers Institute of Technology(国立高等艺术与工艺学院)

Pau Urdeitx, Icíar Alfaro, David González, Francisco Chinesta, Elías Cueto

AI总结:

本文比较了用于热力学信息神经网络的单生成元与双生成元形式化方法,通过经典问题与合成数据实验分析两种方法在满足热力学原理时的优缺点。

摘要:

已有研究表明,开发归纳偏置是提高神经网络准确性和鲁棒性的非常有效的方法,尤其是当神经网络被用于预测物理现象时。这些偏置显著提高了预测的确定性,降低了所产生的误差,并允许使用规模小得多的数据集。文献中存在大量开发这些偏置的方法。在处理物理现象时,最有效的方法之一是将公认有效的物理原理引入网络架构中。当缺乏对所研究现象起支配作用的物理原理的知识时,问题会变得更加复杂。此时一个非常有吸引力的可能性是转向热力学原理,因为热力学原理具有普遍有效性,无论对所研究现象寻求的描述处于何种抽象层次。为了确保满足热力学原理,存在在许多科学分支中具有悠久传统的表述形式。例如,在流变学领域,主要使用两类形式化方法来确保满足这些原理:单生成元形式化和双生成元形式化。本文利用具有已知解的经典问题和合成数据,研究每种方法的优缺点。

英文摘要:

The development of inductive biases has been shown to be a very effective way to increase the accuracy and robustness of neural networks, particularly when they are used to predict physical phenomena. These biases significantly increase the certainty of predictions, decrease the error made and allow considerably smaller datasets to be used. There are a multitude of methods in the literature to develop these biases. One of the most effective ways, when dealing with physical phenomena, is to introduce physical principles of recognised validity into the network architecture. The problem becomes more complex without knowledge of the physical principles governing the phenomena under study. A very interesting possibility then is to turn to the principles of thermodynamics, which are universally valid, regardless of the level of abstraction of the description sought for the phenomenon under study. To ensure compliance with the principles of thermodynamics, there are formulations that have a long tradition in many branches of science. In the field of rheology, for example, two main types of formalisms are used to ensure compliance with these principles: one-generator and two-generator formalisms. In this paper we study the advantages and disadvantages of each, using classical problems with known solutions and synthetic data.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑