TL;DR本研究论文介绍了递归神经网络 (RNN)、 长短期记忆网络 (LSTM)及其变体,在训练过程中解决长序列中的梯度消失/爆炸问题,并详细介绍了LSTM 中的门控单元,双向 RNN 及 Embeddings from Language Model (ELMo) network 的原理。
Abstract
This is a tutorial paper on recurrent neural network (RNN), long short-term memory network (LSTM), and their variants. We start with a dynamical system and backpropagation through time for RNN. Then, we discuss t