|
神经自回归分布估计，以及Yoshua Bengio的相关讨论
The Neural Autoregressive Distribution Estimator, incl. discussion by Yoshua Bengio |
|
| |
| 课程网址: |
http://videolectures.net/aistats2011_larochelle_neural/
|
| 主讲教师: |
Yoshua Bengio; Hugo Larochelle
|
| 开课单位: |
蒙特利尔大学
|
| 开课时间: |
2011-05-06
|
| 课程语种: |
英语
|
| 中文简介: |
描述了一种新的离散变量高维向量分布的建模方法。该模型受限制玻尔兹曼机器（RBM）的启发，该机器已被证明是此类分布的强大模型。然而，RBM通常不提供一个可追踪的分布估计量，因为评估它分配给某些给定观测的概率需要计算所谓的配分函数，即使是中等大小的RBM也难以计算。我们的模型通过将观测的联合分布分解为可跟踪的条件分布，并使用类似于RBM条件的非线性函数对每个条件进行建模，从而规避了这一困难。我们的模型也可以解释为一个有线自动编码器，这样它的输出就可以用来为观测分配有效的概率。我们证明，该模型在多个数据集上优于其他多变量二元分布估计，其性能类似于大型（但难以处理）RBM。
|
| 课程简介: |
We describe a new approach for modeling the distribution of high-dimensional vectors of discrete variables. This model is inspired by the restricted Boltzmann machine (RBM), which has been shown to be a powerful model of such distributions. However, an RBM typically does not provide a tractable distribution estimator, since evaluating the probability it assigns to some given observation requires the computation of the so-called partition function, which itself is intractable for RBMs of even moderate size. Our model circumvents this difficulty by decomposing the joint distribution of observations into tractable conditional distributions and modeling each conditional using a non-linear function similar to a conditional of an RBM. Our model can also be interpreted as an autoencoder wired such that its output can be used to assign valid probabilities to observations. We show that this new model outperforms other multivariate binary distribution estimators on several datasets and performs similarly to a large (but intractable) RBM.
|
| 关 键 词: |
神经自回归分布估计; 概率; 模型; RBM
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2019-12-27：lxf
|
| 阅读次数: |
92
|
|
图 书 馆