반응형
https://youtube.com/playlist?list=PLkDaE6sCZn6F6wUI9tvS_Gw1vaFAx6rd6
https://www.coursera.org/learn/nlp-sequence-models?specialization=deep-learning
Sequence Models (Course 5)
Contents
Week1 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
Week2 Natural Language Processing & Word Embeddings
- Word Representation
- Using Word Embeddings
- Properties of Word Embeddings
- Embedding Matrix3m
- Learning Word Embeddings
- Word2Vec
- Negative Sampling
- GloVe Word Vectors
- Sentiment Classification
- Debiasing Word Embeddings
Week3 Sequence Models & Attention Mechanism
- Basic Models
- Picking the Most Likely Sentence
- Beam Search
- Refinements to Beam Search
- Error Analysis in Beam Search
- Bleu Score (Optional)
- Attention Model Intuition
- Attention Model
- Speech Recognition
- Trigger Word Detection
Week4 Transformer Network
- Transformer Network Intuition
- Self-Attention
- Multi-Head Attention
- Transformer Network
- Conclusion and Thank You!
ref.
https://www.deeplearning.ai/thebatch
https://github.com/amanchadha/coursera-deep-learning-specialization
반응형