Training recurrent neural networksEI

摘要

Recurrent Neural Networks (RNNs) are powerful sequence models that were believed to be difficult to train, and as a result they were rarely used in machine learning applications. This thesis presents methods that overcome the difficulty of training RNNs, and applications of RNNs to challenging problems. We first describe a new probabilistic sequence model that combines Restricted Boltzmann Machines and RNNs. The new model is more powerful than similar models while being less difficult to train.Next, we present a new variant of the Hes...更多
个人信息

 

您的评分 :

Training recurrent neural networks, 2013.

被引用次数252|引用|19
标签
作者
评论