DL : RNN & Sequence Data

Part 5.2 of Deep Learning Specialization

1. Sequence Data

- Speech

- Text

- Video

- Time-series

- DNA

2. RNN & Sequence Data

- One-to-One

- Many to One

- One to Many

- Many to Many

3. RNN as Classifier

3.1 Sentiment Analysis (Many-to-One)

3.2 Word labeling (Many-to-Many : T in = T out)

4. RNN as Generator

4.1 Sequence Generator (Many-to-Many : T in != T out)

- Text paragraph

- Music

- Image Caption

5. RNN as Translator

5.1 Sequence Translator (Many-to-Many : T in != T out)

- Language

- Pattern

- Text <> Speech

- News Style <> Shakespeare Pattern

- Human Style <> Machine Style

(Saturday 9 May 2018 <> 2018–05–09)

6. RNN as Real-Time Application

6.1 Trigger-word Detection

— Start point for real command

(Alexa, What is the weather today ?)

Related Articles

• Neural Network — Part 1.1
• Neural Network — Part 1.2
• Neural Network — Part 2
• Neural Network — Part 3
• CNN — Part 4.1
• CNN — Part 4.2
• RNN — Part 5.1
• RNN — Part 5.2

Reference

Deep Learning Specialization: Convolutional Neural Network (Coursera) (Youtube)