https://www.zybuluo.com/hanxiaoyang/note/404582
Lecture 1：自然語言入門與次嵌入
- 1.1 Intro to NLP and Deep Learning
- 1.2 Simple Word Vector representations: word2vec, GloVe
Lecture 2：詞向量表示：語言模型，softmax分類器，單隱層神經網絡
- 2.1 Advanced word vector representations: language models, softmax, single layer networks
Lecture 3：神經網絡與反向傳播：命名實體識別案例
- 3.1 Neural Networks and backpropagation -- for named entity recognition
Lecture 4：神經網絡與反向傳播實踐與應用建議
- 4.1 Project Advice, Neural Networks and Back-Prop (in full gory detail)
Lecture 5：實際應用技巧：梯度檢查，過擬合，正則化，激勵函數等等的細節
- 5.1 Practical tips: gradient checks, overfitting, regularization, activation functions, details
Lecture 6：Tensorflow介紹
- 6.1 Introduction to Tensorflow
Lecture 7：應用在語言模型和相關任務上的循環神經網絡
- 7.1 Recurrent neural networks -- for language modeling and other tasks
Lecture 8：在機器翻譯等領域廣泛應用的GRU和LSTM
- 8.1 GRUs and LSTMs -- for machine translation
Lecture 9：可用於文本解析的循環神經網絡
- 9.1 Recursive neural networks -- for parsing
Lecture 10：用於其他任務(情感分析，段落分析等)上的循環神經網絡
- 10.1 Recursive neural networks -- for different tasks (e.g. sentiment analysis)
Lecture 11：用於句子分類的卷積神經網絡
- 11.1 Convolutional neural networks -- for sentence classification
Lecture 12：嘉賓講座：Andrew Maas講述語音識別
- 12.1 Guest Lecture with Andrew Maas: Speech recognition
Lecture 13：嘉賓講座：Thang Luong講述機器翻譯
- 13.1 Guest Lecture with Thang Luong: Machine Translation
Lecture 14：嘉賓講座：Quoc Le 講述序列到序列學習與大規模深度學習
- 14.1 Guest Lecture with Quoc Le: Seq2Seq and Large Scale DL
Lecture 15：自然語言處理上深度學習前沿方向：動態記憶網絡
- 15.1 The future of Deep Learning for NLP: Dynamic Memory Networks