https://www.zybuluo.com/hanxiaoyang/note/404582
Lecture 1：自然语言入门与次嵌入
- 1.1 Intro to NLP and Deep Learning
- 1.2 Simple Word Vector representations: word2vec, GloVe
Lecture 2：词向量表示：语言模型，softmax分类器，单隐层神经网络
- 2.1 Advanced word vector representations: language models, softmax, single layer networks
Lecture 3：神经网络与反向传播：命名实体识别案例
- 3.1 Neural Networks and backpropagation — for named entity recognition
Lecture 4：神经网络与反向传播实践与应用建议
- 4.1 Project Advice, Neural Networks and Back-Prop (in full gory detail)
Lecture 5：实际应用技巧：梯度检查，过拟合，正则化，激励函数等等的细节
- 5.1 Practical tips: gradient checks, overfitting, regularization, activation functions, details
Lecture 6：Tensorflow介绍
- 6.1 Introduction to Tensorflow
Lecture 7：应用在语言模型和相关任务上的循环神经网络
- 7.1 Recurrent neural networks — for language modeling and other tasks
Lecture 8：在机器翻译等领域广泛应用的GRU和LSTM
- 8.1 GRUs and LSTMs — for machine translation
Lecture 9：可用于文本解析的循环神经网络
- 9.1 Recursive neural networks — for parsing
Lecture 10：用于其他任务(情感分析，段落分析等)上的循环神经网络
- 10.1 Recursive neural networks — for different tasks (e.g. sentiment analysis)
Lecture 11：用于句子分类的卷积神经网络
- 11.1 Convolutional neural networks — for sentence classification
Lecture 12：嘉宾讲座：Andrew Maas讲述语音识别
- 12.1 Guest Lecture with Andrew Maas: Speech recognition
Lecture 13：嘉宾讲座：Thang Luong讲述机器翻译
- 13.1 Guest Lecture with Thang Luong: Machine Translation
Lecture 14：嘉宾讲座：Quoc Le 讲述序列到序列学习与大规模深度学习
- 14.1 Guest Lecture with Quoc Le: Seq2Seq and Large Scale DL
Lecture 15：自然语言处理上深度学习前沿方向：动态记忆网络
- 15.1 The future of Deep Learning for NLP: Dynamic Memory Networks
