首页> 外文会议>Conference on Neural Information Processing Systems >ODE~2VAE: Deep generative second order ODEs with Bayesian neural networks
【24h】

ODE~2VAE: Deep generative second order ODEs with Bayesian neural networks

机译:ode〜2VAE:贝叶斯神经网络的深生成次阶段

获取原文

摘要

We present Ordinary Differential Equation Variational Auto-Encoder (ODE~2VAE), a latent second order ODE model for high-dimensional sequential data. Leveraging the advances in deep generative models, ODE~2VAE can simultaneously learn the embedding of high dimensional trajectories and infer arbitrarily complex continuous-time latent dynamics. Our model explicitly decomposes the latent space into momentum and position components and solves a second order ODE system, which is in contrast to recurrent neural network (RNN) based time series models and recently proposed black-box ODE techniques. In order to account for uncertainty, we propose probabilistic latent ODE dynamics parameterized by deep Bayesian neural networks. We demonstrate our approach on motion capture, image rotation and bouncing balls datasets. We achieve state-of-the-art performance in long term motion prediction and imputation tasks.
机译:我们呈现普通微分方程变形自动编码器(ODE〜2VAE),用于高维顺序数据的潜在二阶焦点模型。 利用深度生成模型的进步,颂歌〜2VAE可以同时学习高维轨迹的嵌入,并推断任意复杂的连续时间潜行动态。 我们的模型明确地将潜在空间分解为势头和位置组件,并解决了第二阶ode系统,与经常性神经网络(RNN)的时间序列模型相反,最近提出的黑盒颂歌技术。 为了解释不确定性,我们提出了由深贝叶斯神经网络参数化的概率潜在颂歌动态。 我们在运动捕获,图像旋转和弹跳球数据集上展示了我们的方法。 我们在长期运动预测和归纳任务中实现最先进的性能。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号