Recurrent Neural Networks
- Why sequence models
- Notation
- Recurrent neural network model
- Backpropagation through time
- Different types of rnns
- Language model and sequence generation
- Sampling novel sequences
- Vanishing gradients with rnns
- Gated recurrent unit: GRU
- Long short-term memory: LSTM
- Bidirectional rnn
- Deep rnns
Natural Language Processing & Word Embeddings
- Word representation
- Using word embedding
- Properties of word embeddings
- Embedding matrix
- Learning word embeddings
- Word2vec
- Negative sampling
- GloVe word vectors
- Sentiment classification
- Debiasing word embeddings
Sequence to sequence models
- Basic models
- Picking the most likely sentence
- Beam search
- Refinements to beam search
- Error analysis on beam search
- Bleu score(optional)
- Attention model intuition
- Speech recognition
- Trigger word detection
中文总结
