Recurrent neural network( RNN),and specifically a variant with long short-term memory( LSTM),is a very efficient model for processing sequence data. RNN algorithm optimization based on extended unsaturated region is proposed aiming at slow convergence of LSTM RNN. Solution to speed up the RNN training process is proposed based on the reason for slow training process and properties of activation function. Optimization method is verified based on character-level language models. The experimental results show ...
| 
推荐 
点击下列相关研究机构和相关文献作者，可以直接查到这些机构和作者被《中国知识资源总库》收录的其它文献，使您全面了解该机构和该作者的研究动态和历史。
