|
时间序列建模的动态因子图
Dynamic Factor Graphs for Time Series Modeling |
|
| |
| 课程网址: |
http://videolectures.net/ecmlpkdd09_mirowski_dfg/
|
| 主讲教师: |
Piotr Mirowski
|
| 开课单位: |
纽约大学
|
| 开课时间: |
2009-10-20
|
| 课程语种: |
英语
|
| 中文简介: |
本文介绍了一种用连续潜状态变量训练动态因子图（DFG）的方法。 DFG包括对隐藏变量和观测变量之间的联合概率建模的因子，以及对隐藏变量建立动态约束的因子。 DFG为隐藏和观测变量的每个配置分配标量能量。基于辐射的推断过程找到给定观察序列的最小能量状态序列。因为这些因子被设计为确保恒定的分区功能，所以可以通过最小化关于因子参数的训练序列的预期能量来训练它们。这些交替推断和参数更新可以被视为确定性EM类似过程。使用平滑正则化器，DFG显示出重建混沌吸引子并完美地分离独立振荡源的混合物。 DFG在时间序列预测方面优于CATS竞争基准的最着名算法。 DFG还成功地重建了丢失的动作捕捉数据。
|
| 课程简介: |
This article presents a method for training Dynamic Factor Graphs (DFG) with continuous latent state variables. A DFG includes factors modeling joint probabilities between hidden and observed variables, and factors modeling dynamical constraints on hidden variables. The DFG assigns a scalar energy to each configuration of hidden and observed variables. A radient-based inference procedure finds the minimum-energy state sequence for a given observation sequence. Because the factors are designed to ensure a constant partition function, they can be trained by minimizing the expected energy over training sequences with respect to the factors’ parameters. These alternated inference and parameter updates can be seen as a deterministic EM-like procedure. Using smoothing regularizers, DFGs are shown to reconstruct chaotic attractors and to separate a mixture of independent oscillatory sources perfectly. DFGs outperform the best known algorithm on the CATS competition benchmark for time series prediction. DFGs also successfully reconstruct missing motion capture data.
|
| 关 键 词: |
连续潜状态变量; 动态因子图; 隐藏变量
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2019-03-27：lxf
|
| 阅读次数: |
137
|
|
图 书 馆