用于随机视频预测的深度变分 Luenberger 型观测器
Deep Variational Luenberger-type Observer for Stochastic Video Prediction
AI总结：
本研究结合随机状态空间模型与深度神经网络，提出基于变分编码器与 Luenberger 型观测器的深度变分模型，通过推导稳定性理论提升鲁棒性，并在 Bouncing Balls 和 Pendulum 数据集上优于同期工作。
摘要：
考虑到固有的随机性和不确定性，预测未来视频帧极具挑战性。在本研究中，我们通过结合随机状态空间模型的可解释性与深度神经网络的表示学习来研究视频预测问题。我们的模型建立在变分编码器之上，该编码器将输入视频转换到潜在特征空间，并使用 Luenberger 型观测器捕捉潜在特征的动态演化。这使得能够以无监督的方式将视频分解为静态特征和动态。通过推导非线性 Luenberger 型观测器的稳定性理论，特征空间中的隐藏状态对初始值变得不敏感，从而提高了整体模型的鲁棒性。此外，可以推导出数据对数似然的变分下界，以基于变分原理获得易于处理的后验预测分布。最后，提供了在 Bouncing Balls 数据集和 Pendulum 数据集等上的实验，以证明所提出的模型优于同期工作。
英文摘要：
Considering the inherent stochasticity and uncertainty, predicting future video frames is exceptionally challenging. In this work, we study the problem of video prediction by combining interpretability of stochastic state space models and representation learning of deep neural networks. Our model builds upon an variational encoder which transforms the input video into a latent feature space and a Luenberger-type observer which captures the dynamic evolution of the latent features. This enables the decomposition of videos into static features and dynamics in an unsupervised manner. By deriving the stability theory of the nonlinear Luenberger-type observer, the hidden states in the feature space become insensitive with respect to the initial values, which improves the robustness of the overall model. Furthermore, the variational lower bound on the data log-likelihood can be derived to obtain the tractable posterior prediction distribution based on the variational principle. Finally, the experiments such as the Bouncing Balls dataset and the Pendulum dataset are provided to demonstrate the proposed model outperforms concurrent works.
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。
