arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.11083cs.LG
收藏

交互系统的条件神经关系推理

Conditional Neural Relational Inference for Interacting Systems

University of Geneva(日内瓦大学);Geneva School of Business Administration, HES-SO(瑞士西部高等专业学院日内瓦工商管理学院)

Joao A. Candido Ramos, Lionel Blondé, Stéphane Armand, Alexandros Kalousis

摘要:

在这项工作中,我们希望学习模拟相似但不同的相互作用对象组的动态。这些群体遵循一些共同的物理定律,这些定律表现出通过一些矢量描述捕获的特异性。我们开发了一个模型,使我们能够从任何这样的组给出其矢量描述的条件生成。与以前的工作学习动力系统,只能做轨迹完成,并要求轨迹动态的一部分,以提供作为输入的生成时间,我们只使用条件向量没有访问生成时间的轨迹。我们评估我们的模型中的设置建模人类步态,特别是病理人类步态。

英文摘要:

In this work, we want to learn to model the dynamics of similar yet distinct groups of interacting objects. These groups follow some common physical laws that exhibit specificities that are captured through some vectorial description. We develop a model that allows us to do conditional generation from any such group given its vectorial description. Unlike previous work on learning dynamical systems that can only do trajectory completion and require a part of the trajectory dynamics to be provided as input in generation time, we do generation using only the conditioning vector with no access to generation time's trajectories. We evaluate our model in the setting of modeling human gait and, in particular pathological human gait.

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。

↑