论文标题
神经物理学家：从图像序列学习物理动力学
Neural Physicist: Learning Physical Dynamics from Image Sequences
论文作者
论文摘要
我们提出了一种名为“神经物理学家”（Neurphy）的新型结构，该结构直接从图像序列中使用深神经网络学习物理动力学。对于任何物理系统，鉴于全球系统参数，国家的时间演变受到基础物理定律的约束。如何以端到端的方式学习有意义的系统表示，并估算促进长期预测的准确状态过渡动态一直是长期的挑战。在本文中，通过利用代表性学习和状态空间模型（SSM）的最新进展，我们提出了Neurphy，该神经使用变异性自动编码器（VAE）在每个时间步骤，神经过程（NP）中提取基本的马尔可夫动态状态，以提取全球系统参数，并提取非线性的非线性状态状态空间模型来学习物理动力学的横向横向横向横向模型。我们对两个物理实验环境（即阻尼的摆和行星轨道运动）应用神经素，并实现有希望的结果。我们的模型不仅可以提取物理有意义的状态表示形式，而且还可以学习对看不见的图像序列的长期预测的状态过渡动力学。此外，从潜在状态空间的多种维度来看，我们可以轻松地确定基础物理系统的自由度（DOF）。
We present a novel architecture named Neural Physicist (NeurPhy) to learn physical dynamics directly from image sequences using deep neural networks. For any physical system, given the global system parameters, the time evolution of states is governed by the underlying physical laws. How to learn meaningful system representations in an end-to-end way and estimate accurate state transition dynamics facilitating long-term prediction have been long-standing challenges. In this paper, by leveraging recent progresses in representation learning and state space models (SSMs), we propose NeurPhy, which uses variational auto-encoder (VAE) to extract underlying Markovian dynamic state at each time step, neural process (NP) to extract the global system parameters, and a non-linear non-recurrent stochastic state space model to learn the physical dynamic transition. We apply NeurPhy to two physical experimental environments, i.e., damped pendulum and planetary orbits motion, and achieve promising results. Our model can not only extract the physically meaningful state representations, but also learn the state transition dynamics enabling long-term predictions for unseen image sequences. Furthermore, from the manifold dimension of the latent state space, we can easily identify the degree of freedom (DoF) of the underlying physical systems.
