图 书 馆
用于运动风格建模的因子条件受限Boltzmann机Factored Conditional Restricted Boltzmann Machines for Modeling Motion Style |
|
| 课程网址: | http://videolectures.net/icml09_taylor_fcr/ |
| 主讲教师: | Graham Taylor |
| 开课单位: | 圭尔夫大学 |
| 开课时间: | 2009-08-26 |
| 课程语种: | 英语 |
| 中文简介: |  条件受限玻尔兹曼机（CRBM）是最近提出的时间序列模型，该模型具有丰富的分布式隐藏状态，并且可以进行简单而精确的推断。我们基于CRBM提出了一个新模型，该模型保留了其最重要的计算属性，并包括可乘的三向交互作用，该交互作用允许两个单元之间的有效交互权重由第三个单元的动态状态进行调节。我们将乘法模型隐含的三向权重张量分解，将参数的数量从O（N ^ 3）减少到O（N ^ 2）。结果是一个有效，紧凑的模型，我们通过对人体运动进行建模来证明其有效性。像CRBM一样，我们的模型可以通过一组参数捕获各种样式的运动，并且三种方式的交互作用极大地提高了模型混合运动样式或在它们之间平滑过渡的能力。 |
| 课程简介: | The Conditional Restricted Boltzmann Machine (CRBM) is a recently proposed model for time series that has a rich, distributed hidden state and permits simple, exact inference. We present a new model, based on the CRBM that preserves its most important computational properties and includes multiplicative three-way interactions that allow the effective interaction weight between two units to be modulated by the dynamic state of a third unit. We factorize the three-way weight tensor implied by the multiplicative model, reducing the number of parameters from O(N^3) to O(N^2). The result is an efficient, compact model whose effectiveness we demonstrate by modeling human motion. Like the CRBM, our model can capture diverse styles of motion with a single set of parameters, and the three-way interactions greatly improve the model's ability to blend motion styles or to transition smoothly between them. |
| 关 键 词: | 玻尔兹曼机; 模型; 混合运动样式 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2021-02-16：nkq |
| 最后编审: | 2021-09-15：zyk |
| 阅读次数: | 85 |