图 书 馆
凸双层造型Convex Two-Layer Modeling |
|
| 课程网址: | http://videolectures.net/machine_aslan_layer_modeling/ |
| 主讲教师: | Özlem Aslan |
| 开课单位: | 阿尔伯塔大学 |
| 开课时间: | 2014-11-07 |
| 课程语种: | 英语 |
| 中文简介: |  潜在变量预测模型（例如多层网络）在输入和输出之间施加辅助潜在变量，以允许自动推断对预测有用的隐式特征。不幸的是，这样的模型很难训练，因为对潜在变量的推断必须与参数优化同时进行，从而产生高度非凸的问题。而不是提出另一种局部训练方法，我们开发了允许全局训练的隐藏层条件模型的凸松弛。我们的方法扩展了当前的凸建模方法，以处理由非平凡的自适应潜层分隔的两个嵌套非线性。所得到的方法能够获取在相同特征上不能由任何单层模型表示的两层模型，同时提高了局部启发式算法的训练质量。 |
| 课程简介: | Latent variable prediction models, such as multi-layer networks, impose auxiliary latent variables between inputs and outputs to allow automatic inference of implicit features useful for prediction. Unfortunately, such models are difficult to train because inference over latent variables must be performed concurrently with parameter optimization---creating a highly non-convex problem. Instead of proposing another local training method, we develop a convex relaxation of hidden-layer conditional models that admits global training. Our approach extends current convex modeling approaches to handle two nested nonlinearities separated by a non-trivial adaptive latent layer. The resulting methods are able to acquire two-layer models that cannot be represented by any single-layer model over the same features, while improving training quality over local heuristics. |
| 关 键 词: | 预测模型; 凸建模 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-11-10：zyk |
| 最后编审: | 2020-11-10：zyk |
| 阅读次数: | 28 |